no code implementations • COLING 2022 • Wei Huang, Chen Liu, Bo Xiao, Yihua Zhao, Zhaoming Pan, Zhimin Zhang, Xinyun Yang, Guiquan Liu
Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.
no code implementations • 30 Apr 2024 • Wei Huang, Bingyang Zhang, Kaituo Zhang, Hua Gao, Rongchun Wan
The task of anomaly detection is to separate anomalous data from normal data in the dataset.
1 code implementation • 22 Apr 2024 • Wei Huang, Xudong Ma, Haotong Qin, Xingyu Zheng, Chengtao Lv, Hong Chen, Jie Luo, Xiaojuan Qi, Xianglong Liu, Michele Magno
This exploration holds the potential to unveil new insights and challenges for low-bit quantization of LLaMA3 and other forthcoming LLMs, especially in addressing performance degradation problems that suffer in LLM compression.
no code implementations • 16 Apr 2024 • Zhengyang Liang, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue
Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information, requiring minimal computational resources.
no code implementations • 25 Mar 2024 • Kaikang Zhao, Xi Chen, Wei Huang, Liuxin Ding, Xianglong Kong, Fan Zhang
In this work, we aim to enhance ensemble diversity by reducing attack transferability.
no code implementations • 22 Mar 2024 • Yinggui Wang, Wei Huang, Le Yang
Thus, the SLU system needs to ensure that a potential malicious attacker cannot deduce the sensitive attributes of the users, while it should avoid greatly compromising the SLU accuracy.
no code implementations • 2 Mar 2024 • Junwen Xiong, Peng Zhang, Tao You, Chuanyue Li, Wei Huang, Yufei zha
Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions.
1 code implementation • 29 Feb 2024 • Hongxia Li, Wei Huang, Jingya Wang, Ye Shi
Specifically, for each client, we learn a global prompt to extract consensus knowledge among clients, and a local prompt to capture client-specific category characteristics.
no code implementations • 9 Feb 2024 • Lu Chen, Wei Huang, Ruqing Zhang, Wei Chen, Jiafeng Guo, Xueqi Cheng
The key idea is to learn task-required causal factors and only use those to make predictions for a given task.
1 code implementation • 6 Feb 2024 • Wei Huang, Yangdong Liu, Haotong Qin, Ying Li, Shiming Zhang, Xianglong Liu, Michele Magno, Xiaojuan Qi
Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources.
no code implementations • 18 Jan 2024 • Wei Huang, Yinggui Wang, Anda Cheng, Aihui Zhou, Chaofan Yu, Lei Wang
In this paper, we propose a secure distributed LLM based on model slicing.
1 code implementation • 17 Jan 2024 • Mikel De Iturrate Reyzabal, Mingcong Chen, Wei Huang, Sebastien Ourselin, Hongbin Liu
In this paper, we present a new vision-haptic dataset (DaFoEs) with variable soft environments for the training of deep neural models.
2 code implementations • 12 Jan 2024 • Xiaoyu Liu, Yueyi Zhang, Zhiwei Xiong, Wei Huang, Bo Hu, Xiaoyan Sun, Feng Wu
IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.
no code implementations • 27 Dec 2023 • Wei Huang, Jun Wang, Xiaoping Li, Qihang Peng
Orthogonal frequency division multiplexing (OFDM) is a widely adopted wireless communication technique but is sensitive to the carrier frequency offset (CFO).
1 code implementation • NeurIPS 2023 • Zhongyi Cai, Ye Shi, Wei Huang, Jingya Wang
Specifically, the online model learns general knowledge that is shared among all clients, while the offline model is trained locally to learn the specialized knowledge of each individual client.
no code implementations • 13 Dec 2023 • Hao Wu, Shilong Wang, Yuxuan Liang, Zhengyang Zhou, Wei Huang, Wei Xiong, Kun Wang
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community.
no code implementations • 6 Dec 2023 • Xinwei Yuan, Shu Han, Wei Huang, Hongliang Ye, Xianglong Kong, Fan Zhang
In this paper, we propose a novel IDS architecture that can enhance the robustness of IDS against adversarial attacks by combining conventional machine learning (ML) models and Deep Learning models.
no code implementations • 17 Nov 2023 • Wei Huang, Aichun Zhu, Hui Liu
Phenotype-based screening has attracted much attention for identifying cell-active compounds.
no code implementations • NeurIPS 2023 • Yuanyuan Wang, Xi Geng, Wei Huang, Biwei Huang, Mingming Gong
In this paper, we present conditions for identifying the generator of a linear stochastic differential equation (SDE) from the distribution of its solution process with a given fixed initial state.
no code implementations • 18 Oct 2023 • Wei Huang, Fan Gao, Junting Wang, Hao Zhang
Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems.
1 code implementation • 12 Oct 2023 • Jinbo Song, Ruoran Huang, Xinyang Wang, Wei Huang, Qian Yu, Mingming Chen, Yafei Yao, Chaosheng Fan, Changping Peng, Zhangang Lin, Jinghe Hu, Jingping Shao
Industrial systems such as recommender systems and online advertising, have been widely equipped with multi-stage architectures, which are divided into several cascaded modules, including matching, pre-ranking, ranking and re-ranking.
no code implementations • 12 Oct 2023 • Wei Huang, Hao Zhang, Kaitao Meng, Fan Gao, Wenzhou Sun, Jianxu Shu, Tianhe Xu, Deshi Li
To tackle this issue, we propose an iterative ray tracing 3D underwater localization (IRTUL) method for stratification compensation.
no code implementations • 12 Oct 2023 • Wei Huang, Jixuan Zhou, Fan Gao, Jiajun Lu, Sijia Li, Pengfei Wu, Junting Wang, Hao Zhang, Tianhe Xu
The proposal of SSP inversion method greatly improves the convenience and real--time performance, but the accuracy is not as good as the direct measurement method.
1 code implementation • 6 Oct 2023 • Yinda Chen, Wei Huang, Shenglong Zhou, Qi Chen, Zhiwei Xiong
By extracting semantic information from unlabeled data, self-supervised methods can improve the performance of downstream tasks, among which the mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images.
Multi-agent Reinforcement Learning reinforcement-learning +2
no code implementations • 15 Sep 2023 • Junwen Xiong, Peng Zhang, Chuanyue Li, Wei Huang, Yufei zha, Tao You
While many approaches have crafted task-specific training paradigms for either video saliency prediction or video salient object detection tasks, few attention has been devoted to devising a generalized saliency modeling framework that seamlessly bridges both these distinct tasks.
no code implementations • 7 Sep 2023 • Cunhang Fan, Hongyu Zhang, Wei Huang, Jun Xue, JianHua Tao, Jiangyan Yi, Zhao Lv, Xiaopei Wu
Specifically, to effectively represent the non-Euclidean properties of EEG signals, dynamical graph convolutional networks are applied to represent the graph structure of EEG signals, which can also extract crucial features related to auditory spatial attention in EEG signals.
no code implementations • 5 Sep 2023 • Wei Huang, Haotong Qin, Yangdong Liu, Jingzhuo Liang, Yulun Zhang, Ying Li, Xianglong Liu
Mixed-precision quantization leverages multiple bit-width architectures to unleash the accuracy and efficiency potential of quantized models.
no code implementations • 31 Aug 2023 • Qi Chen, Wei Huang, Yueyi Zhang, Zhiwei Xiong
In the second stage, we improve model generalizability on target data by regenerating square masks to get high-quality pseudo labels.
2 code implementations • 25 Aug 2023 • Tong Xie, Yuwei Wan, Wei Huang, Zhenyu Yin, Yixuan Liu, Shaozhou Wang, Qingyuan Linghu, Chunyu Kit, Clara Grazian, Wenjie Zhang, Imran Razzak, Bram Hoex
To add new capabilities in natural science, enabling the acceleration and enrichment of automation of the discovery process, we present DARWIN, a series of tailored LLMs for natural science, mainly in physics, chemistry, and material science.
1 code implementation • 24 Aug 2023 • Lu Chen, Ruqing Zhang, Wei Huang, Wei Chen, Jiafeng Guo, Xueqi Cheng
The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.
no code implementations • 20 Aug 2023 • Wenying Duan, HONG RAO, Wei Huang, Xiaoxi He
Traffic prediction is essential for the progression of Intelligent Transportation Systems (ITS) and the vision of smart cities.
no code implementations • 19 Aug 2023 • Yinda Chen, Wei Huang, Xiaoyu Liu, Shiyu Deng, Qi Chen, Zhiwei Xiong
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations.
1 code implementation • 9 Aug 2023 • Tianyu Liu, Peng Zhang, Wei Huang, Yufei zha, Tao You, Yanning Zhang
By decoupling the gradients of visual and audio modalities, the discriminative visual representations of sound sources can be learned with the designed Induction Vector in a bootstrap manner, which also enables the audio modality to be aligned with the visual modality consistently.
no code implementations • 6 Aug 2023 • Wei Miao, Hong Zhao, Tongjia Chen, Wei Huang, Changyan Xiao
Recent stereo matching networks achieves dramatic performance by introducing epipolar line constraint to limit the matching range of dual-view.
no code implementations • 20 Jul 2023 • Saddek Bensalem, Chih-Hong Cheng, Wei Huang, Xiaowei Huang, Changshun Wu, Xingyu Zhao
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges.
1 code implementation • 10 Jul 2023 • Xiangmeng Wang, Qian Li, Dianer Yu, Wei Huang, Guandong Xu
In this work, we propose to integrate causal modeling with the learning process of GCN-based GCF models, leveraging causality-aware graph embeddings to capture complex causal relations in recommendations.
no code implementations • 8 Jul 2023 • Ganglai Wang, Peng Zhang, Junwen Xiong, Feihan Yang, Wei Huang, Yufei zha
DeepFake based digital facial forgery is threatening public media security, especially when lip manipulation has been used in talking face generation, and the difficulty of fake video detection is further improved.
no code implementations • 24 Jun 2023 • Wei Huang, Yuan Cao, Haonan Wang, Xin Cao, Taiji Suzuki
Graph neural networks (GNNs) have pioneered advancements in graph representation learning, exhibiting superior feature learning and performance over multilayer perceptrons (MLPs) when handling graph inputs.
no code implementations • 7 Jun 2023 • Yinda Chen, Che Liu, Wei Huang, Sibo Cheng, Rossella Arcucci, Zhiwei Xiong
To address these challenges, we present Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation (GTGM), a framework that extends of VLP to 3D medical images without relying on paired textual descriptions.
no code implementations • 22 May 2023 • Xiuzhan Guo, Wei Huang, Min Luo, Priya Rangarajan
Geospatial ontology merging systems, natural partial orders on the systems, and geospatial ontology merging closures in the systems are then transformed under geospatial ontology system homomorphisms that are given by quotients and embeddings.
no code implementations • 19 May 2023 • Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, Andre Freitas, Mustafa A. Mustafa
Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains.
no code implementations • 16 May 2023 • Feng-Lei Fan, Wei Huang, Xiangru Zhong, Lecheng Ruan, Tieyong Zeng, Huan Xiong, Fei Wang
A ReLU network is a piecewise linear function over polytopes.
no code implementations • 11 May 2023 • Zhuoxuan Li, Iakov Korovin, Xinli Shi, Sergey Gorbachev, Nadezhda Gorbacheva, Wei Huang, Jinde Cao
Rutting of asphalt pavements is a crucial design criterion in various pavement design guides.
1 code implementation • NeurIPS 2023 • Yongqiang Chen, Wei Huang, Kaiwen Zhou, Yatao Bian, Bo Han, James Cheng
Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features.
no code implementations • 5 Apr 2023 • Tong Xie, Yuwei Wan, Wei Huang, Yufei Zhou, Yixuan Liu, Qingyuan Linghu, Shaozhou Wang, Chunyu Kit, Clara Grazian, Wenjie Zhang, Bram Hoex
The amount of data has growing significance in exploring cutting-edge materials and a number of datasets have been generated either by hand or automated approaches.
no code implementations • 11 Mar 2023 • Junwen Xiong, Ganglai Wang, Peng Zhang, Wei Huang, Yufei zha, Guangtao Zhai
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain.
1 code implementation • CVPR 2023 • Wei Huang, Zhiliang Peng, Li Dong, Furu Wei, Jianbin Jiao, Qixiang Ye
Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms.
no code implementations • 22 Feb 2023 • Shannan Guan, Xin Yu, Wei Huang, Gengfa Fang, Haiyan Lu
Our DMMG consists of a viewpoint variation min-max game and an edge perturbation min-max game.
no code implementations • 19 Jan 2023 • Chengjie Zhao, Jun Wang, Wei Huang, Xiaonan Chen, Tianfu Qi
Under MGIN channel, classical communication signal schemes and corresponding detection methods usually can not achieve desirable performance as they are optimized with respect to WGN.
1 code implementation • CVPR 2023 • Xiaoyu Liu, Bo Hu, Mingxing Li, Wei Huang, Yueyi Zhang, Zhiwei Xiong
Finally, we provide quantitative and qualitative benchmark comparisons on the testset to validate the superiority of the proposed method, as well as preliminary statistics of the reconstructed somas in the full adult fly brain from the biological perspective.
no code implementations • CVPR 2023 • Junwen Xiong, Ganglai Wang, Peng Zhang, Wei Huang, Yufei zha, Guangtao Zhai
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain.
1 code implementation • ICCV 2023 • Xiaoyu Liu, Wei Huang, Zhiwei Xiong, Shenglong Zhou, Yueyi Zhang, Xuejin Chen, Zheng-Jun Zha, Feng Wu
Sparse instance-level supervision has recently been explored to address insufficient annotation in biomedical instance segmentation, which is easier to annotate crowded instances and better preserves instance completeness for 3D volumetric datasets compared to common semi-supervision. In this paper, we propose a sparsely supervised biomedical instance segmentation framework via cross-representation affinity consistency regularization.
no code implementations • CVPR 2023 • Wei Huang, Chang Chen, Yong Li, Jiacheng Li, Cheng Li, Fenglong Song, Youliang Yan, Zhiwei Xiong
In contrast to existing methods, we instead utilize the difference between images to build a better representation space, where the distinct style features are extracted and stored as the bases of representation.
no code implementations • CVPR 2023 • Jiacheng Li, Chang Chen, Wei Huang, Zhiqiang Lang, Fenglong Song, Youliang Yan, Zhiwei Xiong
Image resampling is a basic technique that is widely employed in daily applications.
no code implementations • 17 Dec 2022 • Pengfei Xi, Guifeng Wang, Zhipeng Hu, Yu Xiong, Mingming Gong, Wei Huang, Runze Wu, Yu Ding, Tangjie Lv, Changjie Fan, Xiangnan Feng
TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy.
1 code implementation • 20 Nov 2022 • Haonan Wang, Jieyu Zhang, Qi Zhu, Wei Huang, Kenji Kawaguchi, Xiaokui Xiao
To answer this question, we theoretically study the concentration property of features obtained by neighborhood aggregation on homophilic and heterophilic graphs, introduce the single-pass augmentation-free graph contrastive learning loss based on the property, and provide performance guarantees for the minimizer of the loss on downstream tasks.
no code implementations • 31 Oct 2022 • Zhenzhe Hechen, Wei Huang, Yixin Zhao
Consequently, this paper presents a light self-limited-attention (LSLA) consisting of a light self-attention mechanism (LSA) to save the computation cost and the number of parameters, and a self-limited-attention mechanism (SLA) to improve the performance.
no code implementations • 30 Oct 2022 • Mengmeng Wu, Ruoxi Jia, Changle lin, Wei Huang, Xiangyu Chang
Data valuation, especially quantifying data value in algorithmic prediction and decision-making, is a fundamental problem in data trading scenarios.
no code implementations • 26 Oct 2022 • Wei Huang, Michelangelo Valsecchi, Michael Multerer
We employ the fully separable wavelet transform and multiwavelets to obtain the anisotropic features to feed to standard CNN classifiers.
no code implementations • 22 Oct 2022 • Wei Huang, Haiyang Zhang, Nir Shlezinger, Yonina C. Eldar
Dynamic metasurface antennas (DMAs) provide a new paradigm to realize large-scale antenna arrays for future wireless systems.
no code implementations • 12 Oct 2022 • Yuanyuan Wang, Wei Huang, Mingming Gong, Xi Geng, Tongliang Liu, Kun Zhang, DaCheng Tao
This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
no code implementations • 12 Oct 2022 • Wei Huang, Jiaxiang Li, Shuming Jiao, Zibang Zhang
Single-pixel imaging (SPI) is a novel optical imaging technique by replacing the pixelated sensor array in a conventional camera with a single-pixel detector.
1 code implementation • 6 Oct 2022 • Songhao Han, Wei Huang, Xiaotian Luan
In our work, we propose a vision-linguistics coordinate time sequence news recommendation.
no code implementations • 7 Sep 2022 • Danru Xu, Erdun Gao, Wei Huang, Menghan Wang, Andy Song, Mingming Gong
Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidential reasoning.
no code implementations • 6 Sep 2022 • Tianfu Qi, Jun Wang, Xiaonan Chen, Wei Huang
In many scenarios, the communication system suffers from both Gaussian white noise and non-Gaussian impulsive noise.
1 code implementation • ICCV 2023 • Wei Huang, Xingyu Zhao, Gaojie Jin, Xiaowei Huang
Finally, we demonstrate two applications of our methods: ranking robust XAI methods and selecting training schemes to improve both classification and interpretation robustness.
1 code implementation • 30 May 2022 • Xiaosong Zhang, Yunjie Tian, Wei Huang, Qixiang Ye, Qi Dai, Lingxi Xie, Qi Tian
A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.
1 code implementation • 27 May 2022 • Erdun Gao, Ignavier Ng, Mingming Gong, Li Shen, Wei Huang, Tongliang Liu, Kun Zhang, Howard Bondell
In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.
1 code implementation • 17 May 2022 • Wei Huang, Xingyu Zhao, Alec Banks, Victoria Cox, Xiaowei Huang
In this paper, we propose a new robustness testing approach for detecting AEs that considers both the feature level distribution and the pixel level distribution, capturing the perceptual quality of adversarial perturbations.
2 code implementations • 11 May 2022 • Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang
Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex.
no code implementations • 7 May 2022 • Shuming Jiao, Jiaxiang Li, Wei Huang, Zibang Zhang
Single-pixel imaging (SPI) is a novel optical imaging technique by replacing a two-dimensional pixelated sensor with a single-pixel detector and pattern illuminations.
no code implementations • 11 Apr 2022 • Haonan Wang, Jieyu Zhang, Qi Zhu, Wei Huang
Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data.
1 code implementation • CVPR 2022 • Gaojie Jin, Xinping Yi, Wei Huang, Sven Schewe, Xiaowei Huang
In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) with respect to the weights.
no code implementations • 10 Mar 2022 • Ganglai Wang, Peng Zhang, Lei Xie, Wei Huang, Yufei zha, Yanning Zhang
DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved.
no code implementations • 8 Mar 2022 • Ganglai Wang, Peng Zhang, Lei Xie, Wei Huang, Yufei zha
Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction.
no code implementations • 5 Mar 2022 • Junwen Xiong, Peng Zhang, Lei Xie, Wei Huang, Yufei zha, Yanning Zhang
Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments.
1 code implementation • 4 Mar 2022 • Junwen Xiong, Yu Zhou, Peng Zhang, Lei Xie, Wei Huang, Yufei zha
Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding.
1 code implementation • ICLR 2022 • Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou
The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart.
no code implementations • 4 Feb 2022 • Wei Huang, Chunrui Liu, Yilan Chen, Tianyu Liu, Richard Yi Da Xu
In addition to being a pure generalization bound analysis tool, PAC-Bayesian bound can also be incorporated into an objective function to train a probabilistic neural network, making them a powerful and relevant framework that can numerically provide a tight generalization bound for supervised learning.
no code implementations • 29 Jan 2022 • Haizhou Du, Ryan Yang, Yijian Chen, Qiao Xiang, Andre Wibisono, Wei Huang
In this paper, we analyze properties of the WPM and rigorously prove convergence properties of our aggregation mechanism.
no code implementations • 24 Jan 2022 • Wei Huang, Tianfu Qi, Yundi Guan, Qihang Peng, Jun Wang
In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system.
no code implementations • 30 Dec 2021 • Zhitong Xiong, Wei Huang, Jingtao Hu, Xiao Xiang Zhu
Therefore, we propose a new benchmark dataset to study the transferability of height estimation models in a cross-dataset setting.
no code implementations • 30 Nov 2021 • Yi Dong, Wei Huang, Vibhav Bharti, Victoria Cox, Alec Banks, Sen Wang, Xingyu Zhao, Sven Schewe, Xiaowei Huang
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety.
1 code implementation • 25 Nov 2021 • Yunjie Tian, Lingxi Xie, Xiaopeng Zhang, Jiemin Fang, Haohang Xu, Wei Huang, Jianbin Jiao, Qi Tian, Qixiang Ye
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.
Ranked #63 on Semantic Segmentation on Cityscapes test
1 code implementation • NeurIPS 2021 • Yilan Chen, Wei Huang, Lam M. Nguyen, Tsui-Wei Weng
Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent.
no code implementations • 16 Oct 2021 • Haonan Wang, Wei Huang, Ziwei Wu, Andrew Margenot, Hanghang Tong, Jingrui He
Active learning theories and methods have been extensively studied in classical statistical learning settings.
1 code implementation • 6 Oct 2021 • Zhiliang Peng, Wei Huang, Zonghao Guo, Xiaosong Zhang, Jianbin Jiao, Qixiang Ye
We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way.
no code implementations • 17 Sep 2021 • Wei Huang, Chen Liu, Yihua Zhao, Xinyun Yang, Zhaoming Pan, Zhimin Zhang, Guiquan Liu
Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.
1 code implementation • 31 Jul 2021 • Jingxian Sun, Lichao Zhang, Yufei zha, Abel Gonzalez-Garcia, Peng Zhang, Wei Huang, Yanning Zhang
To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data.
1 code implementation • 20 Jul 2021 • Shuting Jin, Xiangxiang Zeng, Wei Huang, Feng Xia, Changzhi Jiang, Xiangrong Liu, Shaoliang Peng
The Corona Virus Disease 2019 (COVID-19) belongs to human coronaviruses (HCoVs), which spreads rapidly around the world.
no code implementations • 22 Jun 2021 • Miao Zhang, Wei Huang, Li Wang
We investigate this question through the lens of edge connectivity, and provide an affirmative answer by defining a connectivity concept, ZERo-cost Operation Sensitivity (ZEROS), to score the importance of candidate operations in DARTS at initialization.
1 code implementation • 2 Jun 2021 • Xingyu Zhao, Wei Huang, Alec Banks, Victoria Cox, David Flynn, Sven Schewe, Xiaowei Huang
The utilisation of Deep Learning (DL) is advancing into increasingly more sophisticated applications.
4 code implementations • ICCV 2021 • Zhiliang Peng, Wei Huang, Shanzhi Gu, Lingxi Xie, YaoWei Wang, Jianbin Jiao, Qixiang Ye
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations.
Ranked #325 on Image Classification on ImageNet
1 code implementation • CVPR 2021 • Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao
To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information.
1 code implementation • 16 Apr 2021 • Mingxing Li, Chang Chen, Xiaoyu Liu, Wei Huang, Yueyi Zhang, Zhiwei Xiong
Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.
Ranked #1 on 3D Instance Segmentation on MitoEM
no code implementations • 13 Apr 2021 • Xingyu Zhao, Wei Huang, Sven Schewe, Yi Dong, Xiaowei Huang
The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications.
no code implementations • 24 Mar 2021 • Wei Huang, Richard Combes, Cindy Trinh
We propose a novel algorithm for multi-player multi-armed bandits without collision sensing information.
1 code implementation • CVPR 2021 • Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bing Jiang, Wei Liu
While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content.
no code implementations • 12 Mar 2021 • Chaorong Li, Malu Zhang, Wei Huang, Fengqing Qin, Anping Zeng, Yuanyuan Huang
To address this issue, we use the proposed SRN which composed of BiLSTM and several Tanh-Dropout blocks (called BiLSTM-TDN), to further process DCNN one-dimensional features for highlighting the detail information of image.
no code implementations • ICLR 2022 • Wei Huang, Yayong Li, Weitao Du, Jie Yin, Richard Yi Da Xu, Ling Chen, Miao Zhang
Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.
no code implementations • 16 Feb 2021 • Wei Huang, Oliver Linton, Zheng Zhang
We propose a general framework for the specification testing of continuous treatment effect models.
no code implementations • 18 Dec 2020 • Wei Huang, Tianrui Li, Dexian Wang, Shengdong Du, Junbo Zhang
An appropriate weight selection algorithm that combines the information quantity of training accuracy and training frequency to measure the weights is proposed.
2 code implementations • 5 Dec 2020 • Xingyu Zhao, Wei Huang, Xiaowei Huang, Valentin Robu, David Flynn
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research.
no code implementations • 25 Nov 2020 • Wei Huang, Weitao Du, Richard Yi Da Xu, Chunrui Liu
We claim that depending on the separation conditions of data, the gradient descent iterates will converge to a flatter minimum in the catapult phase.
2 code implementations • 16 Oct 2020 • Wei Huang, Xingyu Zhao, Xiaowei Huang
Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively.
1 code implementation • ECCV 2020 • Hongyu Liu, Bin Jiang, Yibing Song, Wei Huang, Chao Yang
We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively.
no code implementations • 19 May 2020 • Wei Huang, Yong Zeng, Yongming Huang
This paper investigates the achievable rate region of the multiple-input single-output (MISO) interference channel aided by intelligent reflecting surfaces (IRSs).
2 code implementations • 13 Apr 2020 • Wei Huang, Weitao Du, Richard Yi Da Xu
The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training.
1 code implementation • 19 Dec 2019 • Wei Huang, Richard Yi Da Xu, Weitao Du, Yutian Zeng, Yunce Zhao
In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success.
2 code implementations • 19 Dec 2019 • Wei Huang, Richard Yi Da Xu
Our work is primarily inspired by the Gaussian Process Latent Variable Model (GPLVM), which was a non-linear dimensionality reduction method.
no code implementations • 18 Dec 2019 • Hongyu Liu, Bin Jiang, Wei Huang, Chao Yang
However, the two-stage architecture is time-consuming, the contextual information lack high-level semantics and ignores both the semantic relevance and distance information of hole's feature patches, these limitations result in blurry textures and distorted structures of final result.
1 code implementation • 5 Nov 2019 • Wei Huang, Youcheng Sun, Xingyu Zhao, James Sharp, Wenjie Ruan, Jie Meng, Xiaowei Huang
The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.
no code implementations • 30 Jul 2019 • Ron Levie, Wei Huang, Lorenzo Bucci, Michael M. Bronstein, Gitta Kutyniok
Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter or ConvNet should have similar repercussions on both graphs.
1 code implementation • 20 Jun 2019 • Wei Huang, Youcheng Sun, Xiaowei Huang, James Sharp
Recurrent neural networks (RNNs) have been widely applied to various sequential tasks such as text processing, video recognition, and molecular property prediction.
no code implementations • 27 Feb 2019 • Shuzhao Li, Huimin Yu, Wei Huang, Jing Zhang
Person attributes are often exploited as mid-level human semantic information to help promote the performance of person re-identification task.
no code implementations • 1 May 2018 • Wei Huang, Tao Xu, Kangshun Li, Jun He
PMODE and HECO-PDE are compared with the algorithms from the IEEE CEC 2018 competition and another recent MOEA for constrained optimisation.