Search Results for author:
Found 163 papers, 102 papers with code
Federated Learning with Only Positive Labels by Exploring Label Correlations
Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Perfect Reasoners
We evaluate the performance of DUP prompting on ten diverse reasoning datasets.
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts.
A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification
Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap of HSI classification models between pocket models and standard vision backbones.
Improving Bird's Eye View Semantic Segmentation by Task Decomposition
In the first stage, we train a BEV autoencoder to reconstruct the BEV segmentation maps given corrupted noisy latent representation, which urges the decoder to learn fundamental knowledge of typical BEV patterns.
MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks.
Ranked #1 on
Semantic Segmentation
on SpaceNet 1
(using extra training data)
Aerial Scene Classification
Building change detection for remote sensing images
+12
WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising
Second, to better capture high-frequency components and detailed information, Frequency-Aware Multi-scale Loss (FAM) is proposed by effectively utilizing multi-scale feature space.
Online GNN Evaluation Under Test-time Graph Distribution Shifts
This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation.
Multi-modal Auto-regressive Modeling via Visual Words
Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities.
Ranked #25 on
Visual Question Answering
on MM-Vet
When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability
Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised.
Boosting Semi-Supervised Object Detection in Remote Sensing Images With Active Teaching
The lack of object-level annotations poses a significant challenge for object detection in remote sensing images (RSIs).
ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
With the development of instruction-tuned large language models (LLMs), improving the safety of LLMs has become more critical.
Revisiting Knowledge Distillation for Autoregressive Language Models
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model.
FDNet: Frequency Domain Denoising Network For Cell Segmentation in Astrocytes Derived From Induced Pluripotent Stem Cells
Moreover, a novel frequency domain denoising network, named FDNet, is proposed for astrocyte segmentation.
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
In terms of the AMG mode, Hi-SAM segments text stroke foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing.
Ranked #1 on
Hierarchical Text Segmentation
on HierText
Visual Imitation Learning with Calibrated Contrastive Representation
Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions.
MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images
To address these two issues, we propose a novel Masked Autoencoder-enhanced Diffusion Model (MAEDiff) for unsupervised anomaly detection in brain images.
Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models
Recently, the flourishing large language models(LLM), especially ChatGPT, have shown exceptional performance in language understanding, reasoning, and interaction, attracting users and researchers from multiple fields and domains.
Transformer for Object Re-Identification: A Survey
Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from varying viewpoints.
OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models
Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e. g., HumanEval and MBPP.
ChangeCLIP: Remote sensing change detection with multimodal vision-language representation learning
Following this trend, in this study, we introduce ChangeCLIP, a novel framework that leverages robust semantic information from image-text pairs, specifically tailored for Remote Sensing Change Detection (RSCD).
Ranked #4 on
Change Detection
on CDD Dataset (season-varying)
XAI for In-hospital Mortality Prediction via Multimodal ICU Data
To address this issue, this paper proposes an eXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data.
Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification
Skeleton Encoder integrates the local information of neurons in a bottom-up manner, with a one-dimensional convolution in neural skeleton's point data; Connectome Encoder uses a graph neural network to capture the topological information of neural circuit; finally, Readout Layer fuses the above two information and outputs classification results.
Sparse is Enough in Fine-tuning Pre-trained Large Language Model
With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue.
Shifted Autoencoders for Point Annotation Restoration in Object Counting
Object counting typically uses 2D point annotations.
Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion
At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model.
Exploring Sparsity in Graph Transformers
Graph Transformers (GTs) have achieved impressive results on various graph-related tasks.
Adapting Vision Transformer for Efficient Change Detection
Most change detection models based on vision transformers currently follow a "pretraining then fine-tuning" strategy.
UniGS: Unified Representation for Image Generation and Segmentation
On the other hand, the progressive dichotomy module can efficiently decode the synthesized colormap to high-quality entity-level masks in a depth-first binary search without knowing the cluster numbers.
Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodes
Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning.
Learning transformer-based heterogeneously salient graph representation for multimodal fusion classification of hyperspectral image and LiDAR data
Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation.
Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark
In this survey, we provide a systematic overview of the important and recent developments of research on federated learning.
Rotation Invariant Transformer for Recognizing Object in UAVs
Existing methods are usually designed for city cameras, incapable of handing the rotation issue in UAV scenarios.
Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models
The key algorithm in solving ZSAQ is the SAM-SGA optimization, which aims to improve the quantization accuracy and model generalization via optimizing a minimax problem.
Learn From Model Beyond Fine-Tuning: A Survey
LFM focuses on the research, modification, and design of FM based on the model interface, so as to better understand the model structure and weights (in a black box environment), and to generalize the model to downstream tasks.
Imitation Learning from Purified Demonstration
To tackle these problems, we propose to purify the potential perturbations in imperfect demonstrations and subsequently conduct imitation learning from purified demonstrations.
Parameter Efficient Multi-task Model Fusion with Partial Linearization
We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model, outperforming standard adapter tuning and task arithmetic alone.
Zero-shot Learning of Drug Response Prediction for Preclinical Drug Screening
In this paper, we propose a zero-shot learning solution for the DRP task in preclinical drug screening.
Exchange means change: an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange
Change detection (CD) is a critical task in studying the dynamics of ecosystems and human activities using multi-temporal remote sensing images.
Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning
Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data.
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed.
SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images
These CD methods, however, still perform far from satisfactorily as we observe that 1) deep encoder layers focus on irrelevant background regions and 2) the models' confidence in the change regions is inconsistent at different decoder stages.
Enhancing Visually-Rich Document Understanding via Layout Structure Modeling
In this paper, we propose GraphLayoutLM, a novel document understanding model that leverages the modeling of layout structure graph to inject document layout knowledge into the model.
Rethinking the Localization in Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision.
Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
Extensive experiments on both open-source and in-house datasets consistently demonstrate the effectiveness of the proposed method over some CNN and Transformer-based segmentation methods.
IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer
To bridge this gap, based on the fact that artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision that could converge with a small amount of data.
PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels.
Building-road Collaborative Extraction from Remotely Sensed Images via Cross-Interaction
Compared with many existing methods that train each task individually, the proposed collaborative extraction method can utilize the complementary advantages between buildings and roads by the proposed inter-task and inter-scale feature interactions, and automatically select the optimal reception field for different tasks.
DeepCL: Deep Change Feature Learning on Remote Sensing Images in the Metric Space
To address these issues, we complement the strong temporal modeling ability of metric learning with the prominent fitting ability of segmentation and propose a deep change feature learning (DeepCL) framework for robust and explainable CD.
Expediting Building Footprint Extraction from High-resolution Remote Sensing Images via progressive lenient supervision
The efficacy of building footprint segmentation from remotely sensed images has been hindered by model transfer effectiveness.
Heterogeneous Federated Learning: State-of-the-art and Research Challenges
Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential.
Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers
SGD and Adam are two classical and effective optimizers on which researchers have proposed many variants, such as SGDM and RAdam.
On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
A pooling operation is essential for effective graph-level representation learning, where the node drop pooling has become one mainstream graph pooling technology.
FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes
We represent the action information in each hand interaction region as a triplet, resulting in a total of 878 action triplets.
FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction
To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework.
An Efficient Transformer for Simultaneous Learning of BEV and Lane Representations in 3D Lane Detection
Our method obtains 2D and 3D lane predictions by applying the lane features to the image-view and BEV features, respectively.
Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution
(2) For the cross-modality gap, we propose a novel Symmetric Uncertainty scheme to remove parts of RGB information harmful to the recovery of HR depth maps.
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously.
Ranked #1 on
Text Spotting
on Inverse-Text
AIMS: All-Inclusive Multi-Level Segmentation
Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved.
Self-Evolution Learning for Discriminative Language Model Pretraining
Masked language modeling, widely used in discriminative language model (e. g., BERT) pretraining, commonly adopts a random masking strategy.
Revisiting Token Dropping Strategy in Efficient BERT Pretraining
Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers.
Improving Heterogeneous Model Reuse by Density Estimation
This paper studies multiparty learning, aiming to learn a model using the private data of different participants.
Revolutionizing Agrifood Systems with Artificial Intelligence: A Survey
With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages.
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS.
Scalable Mask Annotation for Video Text Spotting
Video text spotting refers to localizing, recognizing, and tracking textual elements such as captions, logos, license plates, signs, and other forms of text within consecutive video frames.
HKNAS: Classification of Hyperspectral Imagery Based on Hyper Kernel Neural Architecture Search
Recent neural architecture search (NAS) based approaches have made great progress in hyperspectral image (HSI) classification tasks.
DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is challenging due to spatial variability caused by complex imaging conditions.
Unsupervised Cross-domain Pulmonary Nodule Detection without Source Data
This motivates us to propose a Source-free Unsupervised cross-domain method for Pulmonary nodule detection (SUP).
EMS-Net: Efficient Multi-Temporal Self-Attention For Hyperspectral Change Detection
Hyperspectral change detection plays an essential role of monitoring the dynamic urban development and detecting precise fine object evolution and alteration.
Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.
Centroid-centered Modeling for Efficient Vision Transformer Pre-training
Our proposed approach, \textbf{CCViT}, leverages k-means clustering to obtain centroids for image modeling without supervised training of tokenizer model.
SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention
To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks.
Token Contrast for Weakly-Supervised Semantic Segmentation
Secondly, to further differentiate the low-confidence regions in CAM, we devised a Class Token Contrast module (CTC) inspired by the fact that class tokens in ViT can capture high-level semantics.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
HCGMNET: A Hierarchical Change Guiding Map Network For Change Detection
Very-high-resolution (VHR) remote sensing (RS) image change detection (CD) has been a challenging task for its very rich spatial information and sample imbalance problem.
Ranked #2 on
Change Detection
on LEVIR+
Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT
Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries.
Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE
This technical report briefly describes our JDExplore d-team's submission Vega v1 on the General Language Understanding Evaluation (GLUE) leaderboard, where GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference.
Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning
In this paper, we propose a Patch-Mixed Cross-Modality framework (PMCM), where two images of the same person from two modalities are split into patches and stitched into a new one for model learning.
Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations.
Rethinking Federated Learning With Domain Shift: A Prototype View
The private model presents degenerative performance on other domains (with domain shift).
Generating Dynamic Kernels via Transformers for Lane Detection
While such methods reduce the reliance on specific knowledge, the kernels computed from the key locations fail to capture the lane line's global structure due to its long and thin structure, leading to inaccurate detection of lane lines with complex topologies.
Ranked #1 on
Lane Detection
on CurveLanes
Diff-Font: Diffusion Model for Robust One-Shot Font Generation
Specifically, a large stroke-wise dataset is constructed, and a stroke-wise diffusion model is proposed to preserve the structure and the completion of each generated character.
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Ranked #1 on
Common Sense Reasoning
on ReCoRD
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously.
Ranked #1 on
Text Spotting
on Total-Text
(using extra training data)
DynamicLight: Dynamically Tuning Traffic Signal Duration with DRL
Deep reinforcement learning (DRL) is becoming increasingly popular in implementing traffic signal control (TSC).
Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models
Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization.
Few-Shot Model Agnostic Federated Learning
To address these issues, this paper presents a novel framework with two main parts: 1) model agnostic federated learning, it performs public-private communication by unifying the model prediction outputs on the shared public datasets; 2) latent embedding adaptation, it addresses the domain gap with an adversarial learning scheme to discriminate the public and private domains.
Unsupervised Multimodal Change Detection Based on Structural Relationship Graph Representation Learning
Subsequently, the similarity levels of two structural relationships are calculated from learned graph representations and two difference images are generated based on the similarity levels.
Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition
To address the above issues, we propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition.
PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks.
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability.
Ranked #1 on
Aerial Scene Classification
on AID (50% as trainset)
LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection
Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection.
Leveraging GAN Priors for Few-Shot Part Segmentation
Overall, this work is an attempt to explore the internal relevance between generation tasks and perception tasks by prompt designing.
Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks
However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where significant redundancy exists.
Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit.
DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling. In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation.
Ranked #3 on
Scene Text Detection
on SCUT-CTW1500
What Makes for Automatic Reconstruction of Pulmonary Segments
The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing.
CLNode: Curriculum Learning for Node Classification
Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.
E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
To verify our hypothesis, we first empirically study the functionalities of the encoder and decoder in seq2seq pretrained language models, and find that the encoder takes an important but under-exploitation role than the decoder regarding the downstream performance and neuron activation.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
Multi-Temporal Spatial-Spectral Comparison Network for Hyperspectral Anomalous Change Detection
Hyperspectral anomalous change detection has been a challenging task for its emphasis on the dynamics of small and rare objects against the prevalent changes.
Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities
Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation.
An Empirical Study of Remote Sensing Pretraining
To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.
Ranked #1 on
Aerial Scene Classification
on UCM (80% as trainset)
Aerial Scene Classification
Building change detection for remote sensing images
+5
An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection
In this paper, we propose an end-to-end Supervised Domain Adaptation framework for cross-domain Change Detection, namely SDACD, to effectively alleviate the domain shift between bi-temporal images for better change predictions.
Change Detection
Change detection for remote sensing images
+1
Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers
Motivated by the inherent consistency between the self-attention in Transformers and the semantic affinity, we propose an Affinity from Attention (AFA) module to learn semantic affinity from the multi-head self-attention (MHSA) in Transformers.
Ranked #28 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Multi-Tailed Vision Transformer for Efficient Inference
To satisfy the sequential input of Transformer, the tail of ViT first splits each image into a sequence of visual tokens with a fixed length.
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
In the visual words learning module, we counter the first problem by enforcing the classification network to learn fine-grained visual word labels so that more object extents could be discovered.
Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation
To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
Fully Convolutional Change Detection Framework with Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection
Deep learning for change detection is one of the current hot topics in the field of remote sensing.
Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis
To this end, we propose a knowledge graph augmented network KGAN, which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Learn From Others and Be Yourself in Heterogeneous Federated Learning
Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data.
Multi-Marginal Contrastive Learning for Multi-Label Subcellular Protein Localization
In this paper, we propose a deep protein subcellular localization method with multi-marginal contrastive learning to perceive the same PSLs in different tissue images and different PSLs within the same tissue image.
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.
Ranked #9 on
Scene Text Recognition
on ICDAR2015
(using extra training data)
Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
Many studies confirmed that a proper traffic state representation is more important than complex algorithms for the classical traffic signal control (TSC) problem.
Self-Ensembling GAN for Cross-Domain Semantic Segmentation
In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.
Binary Change Guided Hyperspectral Multiclass Change Detection
In this study, we proposed an unsupervised Binary Change Guided hyperspectral multiclass change detection Network (BCG-Net) for HMCD, which aims at boosting the multiclass change detection result and unmixing result with the mature binary change detection approaches.
Efficient Pressure: Improving efficiency for signalized intersections
Since conventional approaches could not adapt to dynamic traffic conditions, reinforcement learning (RL) has attracted more attention to help solve the traffic signal control (TSC) problem.
MixSiam: A Mixture-based Approach to Self-supervised Representation Learning
In this way, the model could access more variant data samples of an instance and keep predicting invariant discriminative representations for them.
Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
In practice, we formulate the model pretrained on the sampled instances into a knowledge guidance model and a learner model, respectively.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
SGEN: Single-cell Sequencing Graph Self-supervised Embedding Network
This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot.
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
To this end, a semantic-edge domain adaptation architecture is proposed, which uses an independent edge stream to process edge information, thereby generating high-quality semantic boundaries over the target domain.
Ranked #34 on
Synthetic-to-Real Translation
on GTAV-to-Cityscapes Labels
(using extra training data)
Self-supervised Contrastive Learning for EEG-based Sleep Staging
In detail, the network's performance depends on the choice of transformations and the amount of unlabeled data used in the training process of self-supervised learning.
Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images
With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet.
DeepFake MNIST+: A DeepFake Facial Animation Dataset
It includes 10, 000 facial animation videos in ten different actions, which can spoof the recent liveness detectors.
Unsupervised Person Re-identification with Stochastic Training Strategy
State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to store instance features and represent the centroid of the clusters for contrastive learning.
I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i. e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse background context.
Ranked #5 on
Scene Text Detection
on SCUT-CTW1500
Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification
To tackle these problems, in this paper, different from previous approaches, we perform the superpixel generation on intermediate features during network training to adaptively produce homogeneous regions, obtain graph structures, and further generate spatial descriptors, which are served as graph nodes.
Robust Self-Ensembling Network for Hyperspectral Image Classification
Since the collection of pixel-level annotations for HSI is laborious and time-consuming, developing algorithms that can yield good performance in the small sample size situation is of great significance.
Transportation Density Reduction Caused by City Lockdowns Across the World during the COVID-19 Epidemic: From the View of High-resolution Remote Sensing Imagery
Considering that public transportation was mostly reduced or even forbidden, our results indicate that city lockdown policies are effective at limiting human transmission within cities.
LocalDrop: A Hybrid Regularization for Deep Neural Networks
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas.
A high-sensitivity fiber-coupled diamond magnetometer with surface coating
Nitrogen-vacancy quantum defects in diamond offer a promising platform for magnetometry because of their remarkable optical and spin properties.
Applied Physics Quantum Physics
Not All Operations Contribute Equally: Hierarchical Operation-Adaptive Predictor for Neural Architecture Search
Despite their efficiency, current graph-based predictors treat all operations equally, resulting in biased topological knowledge of cell architectures.
Channel Augmented Joint Learning for Visible-Infrared Recognition
This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem.
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment
Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint.
Leveraged Matrix Completion with Noise
In this paper, we employ the leverage scores to characterize the importance of each element and significantly relax assumptions to: (1) not any other structure assumptions are imposed on the underlying low-rank matrix; (2) elements being observed are appropriately dependent on their importance via the leverage score.
Hyperspectral Anomaly Change Detection Based on Auto-encoder
In the ACDA model, two systematic auto-encoder (AE) networks are deployed to construct two predictors from two directions.
Semantic Change Detection with Asymmetric Siamese Networks
Given two multi-temporal aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries.
Recurrent Feature Reasoning for Image Inpainting
To capture information from distant places in the feature map for RFR, we further develop KCA and incorporate it in RFR.
Designing and Training of A Dual CNN for Image Denoising
The enhancement block gathers and fuses the global and local features to provide complementary information for the latter network.
Tchebycheff Procedure for Multi-task Text Classification
Multi-task Learning methods have achieved great progress in text classification.
An Investigation of Traffic Density Changes inside Wuhan during the COVID-19 Epidemic with GF-2 Time-Series Images
The significant reduction and recovery of traffic density indicates that the lockdown policy in Wuhan show effectiveness in controlling human transmission inside the city, and the city returned to normal after lockdown lift.
DSDANet: Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection
By optimizing the network parameters and kernel coefficients with the source labeled data and target unlabeled data, DSDANet can learn transferrable feature representation that can bridge the discrepancy between two domains.
Self-supervised Training of Graph Convolutional Networks
Furthermore, the adjacency matrix is usually pre-defined and stationary, which makes the data augmentation strategies cannot be employed on the constructed graph structures data to augment the amount of training data.
Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion
In this work, we proposed a CorrFusion module that fuses the highly correlated components in bi-temporal feature embeddings.
TextFuseNet: Scene Text Detection with Richer Fused Features
More specifically, we propose to perceive texts from three levels of feature representations, i. e., character-, word- and global-level, and then introduce a novel text representation fusion technique to help achieve robust arbitrary text detection.
Ranked #1 on
Scene Text Detection
on ICDAR 2015
Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection in Multispectral Images
In this paper, we propose a novel deep siamese domain adaptation convolutional neural network (DSDANet) architecture for cross-domain change detection.
OASIS: One-pass aligned Atlas Set for Image Segmentation
Furthermore, instead of using image based similarity for label fusion, which can be distracted by the large background areas, we propose a novel strategy to compute the label similarity based weights for label fusion.
Multi-hop Convolutions on Weighted Graphs
To address the above weaknesses, in this paper, we propose a new method of multi-hop convolutional network on weighted graphs.
Unified Multi-scale Feature Abstraction for Medical Image Segmentation
Automatic medical image segmentation, an essential component of medical image analysis, plays an importantrole in computer-aided diagnosis.
Change Detection in Multi-temporal VHR Images Based on Deep Siamese Multi-scale Convolutional Networks
Based on the unit two novel deep siamese convolutional neural networks, called as deep siamese multi-scale convolutional network (DSMS-CN) and deep siamese multi-scale fully convolutional network (DSMS-FCN), are designed for unsupervised and supervised change detection, respectively.
Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification
To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information.
Exploring Representativeness and Informativeness for Active Learning
Then can we find a way to fuse the two active sampling criteria without any assumption on data?
Robust and Discriminative Labeling for Multi-label Active Learning Based on Maximum Correntropy Criterion
Meanwhile, it is also hard to build a good model without diagnosing discriminative labels.
Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Images
In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier.
Fast Spatio-Temporal Residual Network for Video Super-Resolution
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance.
Boundary-weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation
To make the network more sensitive to the boundaries during segmentation, a boundary-weighted segmentation loss (BWL) is proposed.
Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
In recent years, deep network has shown its brilliant performance in many fields including feature extraction and projection.
Defect Detection from UAV Images based on Region-Based CNNs
In this work, we study the performance of the region-based CNN for the electrical equipment defect detection by using the UAV images.
TLR: Transfer Latent Representation for Unsupervised Domain Adaptation
Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains.
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #15 on
Unsupervised Domain Adaptation
on Market to Duke
Hyperspectral image classification via a random patches network
Due to the remarkable achievements obtained by deep learning methods in the fields of computer vision, an increasing number of researches have been made to apply these powerful tools into hyperspectral image (HSI) classification.
Object Tracking in Satellite Videos Based on a Multi-Frame Optical Flow Tracker
Object tracking is a hot topic in computer vision.
Deeply-Supervised CNN for Prostate Segmentation
Prostate segmentation from Magnetic Resonance (MR) images plays an important role in image guided interven- tion.
A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data
For the second target, a novel CNN-based universal framework is proposed to process the VHR satellite images and generate the land-use, urban density, and population distribution maps.
