3 code implementations • ECCV 2020 • Xiaotong Luo, Yuan Xie, Yulun Zhang, Yanyun Qu, Cuihua Li, Yun Fu
Drawing lessons from lattice filter bank, we design the lattice block (LB) in which two butterfly structures are applied to combine two RBs.
1 code implementation • 27 May 2024 • Yi Xu, Yun Fu
To the best of our knowledge, this is the first work that addresses this unified problem through a versatile generative framework, thereby enhancing our understanding of multi-agent movement.
no code implementations • 16 Apr 2024 • Zaid Khan, Yun Fu
We find that neighborhood consistency can be used to identify model responses to visual questions that are likely unreliable, even in adversarial settings or settings that are out-of-distribution to the proxy model.
no code implementations • 6 Apr 2024 • Zaid Khan, Vijay Kumar BG, Samuel Schulter, Yun Fu, Manmohan Chandraker
We propose a method where we exploit existing annotations for a vision-language task to improvise a coarse reward signal for that task, treat the LLM as a policy, and apply reinforced self-training to improve the visual program synthesis ability of the LLM for that task.
1 code implementation • 2 Apr 2024 • Haichao Zhang, Yi Xu, HongSheng Lu, Takayuki Shimizu, Yun Fu
By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments.
no code implementations • 31 Mar 2024 • Yi Xu, Yun Fu
Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding.
2 code implementations • 29 Mar 2024 • Xu Ma, Xiyang Dai, Yue Bai, Yizhou Wang, Yun Fu
Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design.
1 code implementation • 29 Mar 2024 • Xu Ma, Xiyang Dai, Jianwei Yang, Bin Xiao, Yinpeng Chen, Yun Fu, Lu Yuan
We demonstrate that the modulation mechanism is particularly well suited for efficient networks and further tailor the modulation design by proposing the efficient modulation (EfficientMod) block, which is considered the essential building block for our networks.
1 code implementation • 14 Mar 2024 • Yitian Zhang, Yue Bai, Huan Wang, Yizhou Wang, Yun Fu
Current training pipelines in object recognition neglect Hue Jittering when doing data augmentation as it not only brings appearance changes that are detrimental to classification, but also the implementation is inefficient in practice.
no code implementations • 4 Dec 2023 • Yizhou Wang, Ruiyi Zhang, Haoliang Wang, Uttaran Bhattacharya, Yun Fu, Gang Wu
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs).
no code implementations • 9 Oct 2023 • Haichao Zhang, Yi Xu, HongSheng Lu, Takayuki Shimizu, Yun Fu
In summary, our approach offers a promising solution to the challenges faced by layout sequence and trajectory prediction models in real-world settings, paving the way for utilizing sensor data from mobile phones to accurately predict pedestrian bounding box trajectories.
no code implementations • NeurIPS 2023 • Jianglin Lu, Yi Xu, Huan Wang, Yue Bai, Yun Fu
We begin by defining the pivotal nodes as $k$-hop starved nodes, which can be identified based on a given adjacency matrix.
no code implementations • 13 Aug 2023 • Haichao Zhang, Can Qin, Yu Yin, Yun Fu
This approach can serve as a plug-and-play data generation and augmentation module for existing camouflaged object detection tasks and provides a novel way to introduce more diversity and distributions into current camouflage datasets.
no code implementations • ICCV 2023 • Miaoyu Li, Yachao Zhang, Xu Ma, Yanyun Qu, Yun Fu
In light of this, we propose cross-modal learning under bird's-eye view for Domain Generalization (DG) of 3D semantic segmentation, called BEV-DG.
1 code implementation • CVPR 2023 • Zaid Khan, Vijay Kumar BG, Samuel Schulter, Xiang Yu, Yun Fu, Manmohan Chandraker
We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets.
no code implementations • NeurIPS 2023 • Yanyu Li, Huan Wang, Qing Jin, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, Jian Ren
We achieve so by introducing efficient network architecture and improving step distillation.
1 code implementation • NeurIPS 2023 • Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, Stefano Ermon, Yun Fu, ran Xu
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
1 code implementation • CVPR 2023 • Yi Xu, Armin Bazarjani, Hyung-gun Chi, Chiho Choi, Yun Fu
As far as we know, this is the first work to address the lack of benchmarks and techniques for trajectory imputation and prediction in a unified manner.
2 code implementations • CVPR 2023 • Yitian Zhang, Yue Bai, Chang Liu, Huan Wang, Sheng Li, Yun Fu
To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.
1 code implementation • 21 Mar 2023 • Zaid Khan, Yun Fu
We find that a minimal set of parameter updates ($<$7%) can achieve the same performance as full-model training, and updating specific components ($<$1% of parameters) can match 75% of full-model training.
1 code implementation • ICCV 2023 • Can Qin, Ning Yu, Chen Xing, Shu Zhang, Zeyuan Chen, Stefano Ermon, Yun Fu, Caiming Xiong, ran Xu
Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation.
2 code implementations • ICCV 2023 • Jiamian Wang, Huan Wang, Yulun Zhang, Yun Fu, Zhiqiang Tao
Second, existing pruning methods generally operate upon a pre-trained network for the sparse structure determination, hard to get rid of dense model training in the traditional SR paradigm.
2 code implementations • 2 Mar 2023 • Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, Yun Fu
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
1 code implementation • 13 Feb 2023 • Yizhou Wang, Dongliang Guo, Sheng Li, Octavia Camps, Yun Fu
This paper provides the first survey concentrated on explainable visual anomaly detection methods.
1 code implementation • 28 Jan 2023 • Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, Yun Fu
With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction.
2 code implementations • 12 Jan 2023 • Huan Wang, Can Qin, Yue Bai, Yun Fu
The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to "a lack of standardized benchmarks and metrics" [3].
no code implementations • ICCV 2023 • Yuxiang Lan, Yachao Zhang, Xu Ma, Yanyun Qu, Yun Fu
Spiking Neural Networks (SNNs) have attracted enormous research interest due to their low-power and biologically plausible nature.
1 code implementation • 23 Dec 2022 • Xu Ma, Huan Wang, Can Qin, Kunpeng Li, Xingchen Zhao, Jie Fu, Yun Fu
Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism.
1 code implementation • CVPR 2023 • Junli Cao, Huan Wang, Pavlo Chemerys, Vladislav Shakhrai, Ju Hu, Yun Fu, Denys Makoviichuk, Sergey Tulyakov, Jian Ren
Nevertheless, to reach a similar rendering quality as NeRF, the network in NeLF is designed with intensive computation, which is not mobile-friendly.
no code implementations • CVPR 2023 • Yu Yin, Kamran Ghasedi, HsiangTao Wu, Jiaolong Yang, Xin Tong, Yun Fu
Furthermore, our method leverages explicit and implicit 3D regularizations using the in-domain neighborhood samples around the optimized latent code to remove geometrical and visual artifacts.
1 code implementation • 18 Nov 2022 • Yitian Zhang, Yue Bai, Huan Wang, Yi Xu, Yun Fu
To tackle this problem, we propose Ample and Focal Network (AFNet), which is composed of two branches to utilize more frames but with less computation.
1 code implementation • 13 Oct 2022 • Yue Bai, Huan Wang, Xu Ma, Yitian Zhang, Zhiqiang Tao, Yun Fu
We validate the potential of PEMN learning masks on random weights with limited unique values and test its effectiveness for a new compression paradigm based on different network architectures.
1 code implementation • 25 Jul 2022 • Huan Wang, Yun Fu
Moreover, results on ImageNet-1K with ResNets suggest that TPP consistently performs more favorably against other top-performing structured pruning approaches.
1 code implementation • CVPR 2022 • Xu Ma, Yuqian Zhou, Xingqian Xu, Bin Sun, Valerii Filev, Nikita Orlov, Yun Fu, Humphrey Shi
Image rasterization is a mature technique in computer graphics, while image vectorization, the reverse path of rasterization, remains a major challenge.
1 code implementation • 13 May 2022 • Xingchen Zhao, Chang Liu, Anthony Sicilia, Seong Jae Hwang, Yun Fu
Thus, it is still possible that those methods can overfit to source domains and perform poorly on target domains.
1 code implementation • 31 Mar 2022 • Huan Wang, Jian Ren, Zeng Huang, Kyle Olszewski, Menglei Chai, Yun Fu, Sergey Tulyakov
On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to one single forward pass without ray-marching.
1 code implementation • 27 Mar 2022 • Zaid Khan, Vijay Kumar BG, Xiang Yu, Samuel Schulter, Manmohan Chandraker, Yun Fu
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global level.
1 code implementation • 16 Mar 2022 • Bin Sun, Yulun Zhang, Songyao Jiang, Yun Fu
In this paper, we propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
no code implementations • CVPR 2022 • Yi Xu, Lichen Wang, Yizhou Wang, Yun Fu
To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.
1 code implementation • ICLR 2022 • Yue Bai, Huan Wang, Zhiqiang Tao, Kunpeng Li, Yun Fu
In this work, we regard the winning ticket from LTH as the subnetwork which is in trainable condition and its performance as our benchmark, then go from a complementary direction to articulate the Dual Lottery Ticket Hypothesis (DLTH): Randomly selected subnetworks from a randomly initialized dense network can be transformed into a trainable condition and achieve admirable performance compared with LTH -- random tickets in a given lottery pool can be transformed into winning tickets.
1 code implementation • ICLR 2022 • Xu Ma, Can Qin, Haoxuan You, Haoxi Ran, Yun Fu
We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively.
Ranked #4 on Point Cloud Segmentation on PointCloud-C
Point Cloud Segmentation Supervised Only 3D Point Cloud Classification
1 code implementation • 12 Dec 2021 • Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu
Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
1 code implementation • NeurIPS 2021 • Can Qin, Handong Zhao, Lichen Wang, Huan Wang, Yulun Zhang, Yun Fu
For slow learning of graph similarity, this paper proposes a novel early-fusion approach by designing a co-attention-based feature fusion network on multilevel GNN features.
1 code implementation • NeurIPS 2021 • Yulun Zhang, Huan Wang, Can Qin, Yun Fu
To address the above issues, we propose aligned structured sparsity learning (ASSL), which introduces a weight normalization layer and applies $L_2$ regularization to the scale parameters for sparsity.
1 code implementation • 25 Nov 2021 • Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu, Yue Bai, Yun Fu
Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features.
1 code implementation • 31 Oct 2021 • Joseph P. Robinson, Can Qin, Ming Shao, Matthew A. Turk, Rama Chellappa, Yun Fu
Recognizing Families In the Wild (RFIW), held as a data challenge in conjunction with the 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG), is a large-scale, multi-track visual kinship recognition evaluation.
2 code implementations • 12 Oct 2021 • Songyao Jiang, Bin Sun, Lichen Wang, Yue Bai, Kunpeng Li, Yun Fu
Current Sign Language Recognition (SLR) methods usually extract features via deep neural networks and suffer overfitting due to limited and noisy data.
no code implementations • 29 Sep 2021 • Zaid Khan, Yun Fu
A commonly held belief in deep-learning based long-tailed classification is that the representations learned from long-tailed data are ”good enough” and the performance bottleneck is the classification head atop the representation learner.
no code implementations • 29 Sep 2021 • Huan Wang, Yun Fu
In this paper, we present \emph{orthogonality preserving pruning} (OPP), a regularization-based structured pruning method that maintains the dynamical isometry during pruning.
no code implementations • 29 Sep 2021 • Jiamian Wang, Yulun Zhang, Xin Yuan, Yun Fu, Zhiqiang Tao
As the inverse process of snapshot compressive imaging, the hyperspectral image (HSI) reconstruction takes the 2D measurement as input and posteriorly retrieves the captured 3D spatial-spectral signal.
no code implementations • 29 Sep 2021 • Huan Wang, Suhas Lohit, Michael Jeffrey Jones, Yun Fu
We achieve new state-of-the-art accuracy by using the original KD loss armed with stronger augmentation schemes, compared to existing state-of-the-art methods that employ more advanced distillation losses.
no code implementations • CVPR 2022 • Chang Liu, Xiang Yu, Yi-Hsuan Tsai, Ramin Moslemi, Masoud Faraki, Manmohan Chandraker, Yun Fu
Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data.
no code implementations • 29 Sep 2021 • Huan Wang, Can Qin, Yue Bai, Yun Fu
Several recent works questioned the value of inheriting weight in structured neural network pruning because they empirically found training from scratch can match or even outperform finetuning a pruned model.
no code implementations • ICLR 2022 • Yulun Zhang, Huan Wang, Can Qin, Yun Fu
Specifically, for the layers connected by the same residual, we select the filters of the same indices as unimportant filters.
no code implementations • 29 Sep 2021 • Yi Xu, Lichen Wang, Yizhou Wang, Can Qin, Yulun Zhang, Yun Fu
In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning.
1 code implementation • 17 Aug 2021 • Jiamian Wang, Yulun Zhang, Xin Yuan, Yun Fu, Zhiqiang Tao
The emerging technology of snapshot compressive imaging (SCI) enables capturing high dimensional (HD) data in an efficient way.
1 code implementation • 3 Aug 2021 • Zaid Khan, Yun Fu
Our approach increases the amount of text available to the language model and distills the object-level information in complex images.
1 code implementation • 22 Jun 2021 • Yizhou Wang, Yue Kang, Can Qin, Huan Wang, Yi Xu, Yulun Zhang, Yun Fu
The intuition is that gradient with momentum contains more accurate directional information and therefore its second moment estimation is a more favorable option for learning rate scaling than that of the raw gradient.
no code implementations • CVPR 2021 • Yulun Zhang, Kai Li, Kunpeng Li, Yun Fu
They also fail to sense the entire space of the input, which is critical for high-quality MR image SR. To address those problems, we propose squeeze and excitation reasoning attention networks (SERAN) for accurate MR image SR. We propose to squeeze attention from global spatial information of the input and obtain global descriptors.
Ranked #2 on Image Super-Resolution on IXI
no code implementations • 12 May 2021 • Huan Wang, Can Qin, Yue Bai, Yun Fu
This paper is meant to explain it through the lens of dynamical isometry [42].
1 code implementation • ICCV 2021 • Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, Yun Fu
This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain.
no code implementations • 18 Apr 2021 • Kai Li, Curtis Wigington, Chris Tensmeyer, Vlad I. Morariu, Handong Zhao, Varun Manjunatha, Nikolaos Barmpalios, Yun Fu
Contrasted with prior work, this paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.
1 code implementation • 15 Apr 2021 • Xiaoyu Xiang, Yapeng Tian, Yulun Zhang, Yun Fu, Jan P. Allebach, Chenliang Xu
A na\"ive method is to decompose it into two sub-tasks: video frame interpolation (VFI) and video super-resolution (VSR).
Space-time Video Super-resolution Video Frame Interpolation +1
3 code implementations • 16 Mar 2021 • Songyao Jiang, Bin Sun, Lichen Wang, Yue Bai, Kunpeng Li, Yun Fu
Sign language is commonly used by deaf or speech impaired people to communicate but requires significant effort to master.
Ranked #2 on Sign Language Recognition on WLASL-2000
1 code implementation • 16 Mar 2021 • Joseph P Robinson, Can Qin, Yann Henon, Samson Timoner, Yun Fu
This scheme boosts the average performance and preserves identity information while removing demographic knowledge.
2 code implementations • 11 Mar 2021 • Huan Wang, Can Qin, Yue Bai, Yulun Zhang, Yun Fu
Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network.
1 code implementation • 10 Feb 2021 • Sara Bunian, Kai Li, Chaima Jemmali, Casper Harteveld, Yun Fu, Magy Seif El-Nasr
By utilizing this dataset, we propose an object-detection based image retrieval framework that models the UI context and hierarchical structure.
no code implementations • 3 Feb 2021 • Zaid Khan, Yun Fu
Using the insight that a classifier can learn the racial system encoded by a dataset, we conduct an empirical study of computer vision datasets supplying categorical race labels for face images to determine the cross-dataset consistency and generalization of racial categories.
no code implementations • 11 Jan 2021 • Kunpeng Li, Zizhao Zhang, Guanhang Wu, Xuehan Xiong, Chen-Yu Lee, Zhichao Lu, Yun Fu, Tomas Pfister
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
no code implementations • ICCV 2021 • Yulun Zhang, Donglai Wei, Can Qin, Huan Wang, Hanspeter Pfister, Yun Fu
However, the basic convolutional layer in CNNs is designed to extract local patterns, lacking the ability to model global context.
no code implementations • 1 Jan 2021 • Kunpeng Li, Zizhao Zhang, Guanhang Wu, Xuehan Xiong, Chen-Yu Lee, Yun Fu, Tomas Pfister
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
no code implementations • 1 Jan 2021 • Chang Liu, Kai Li, Yun Fu
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data in a target domain with labeled data from source domain available.
no code implementations • ICCV 2021 • Salma Abdel Magid, Yulun Zhang, Donglai Wei, Won-Dong Jang, Zudi Lin, Yun Fu, Hanspeter Pfister
Specifically, we propose a dynamic high-pass filtering (HPF) module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals.
no code implementations • 1 Jan 2021 • Lichen Wang, Bo Zong, Yunyu Liu, Can Qin, Wei Cheng, Wenchao Yu, Xuchao Zhang, Haifeng Chen, Yun Fu
As texts always contain a large proportion of task-irrelevant words, accurate alignment between aspects and their sentimental descriptions is the most crucial and challenging step.
1 code implementation • ICLR 2021 • Huan Wang, Can Qin, Yulun Zhang, Yun Fu
Regularization has long been utilized to learn sparsity in deep neural network pruning.
no code implementations • 12 Dec 2020 • Yu Yin, Joseph P. Robinson, Yun Fu
Typically, humans are covered by a blanket when resting, for which we propose a multimodal approach to uncover the subjects so their bodies at rest can be viewed without the occlusion of the blankets above.
no code implementations • 7 Dec 2020 • Yu Yin, Joseph P. Robinson, Songyao Jiang, Yue Bai, Can Qin, Yun Fu
Even as impressive milestones are achieved in synthesizing faces, the importance of preserving identity is needed in practice and should not be overlooked.
no code implementations • 5 Dec 2020 • Huan Wang, Suhas Lohit, Michael Jones, Yun Fu
We add loss terms for training the student that measure the dissimilarity between student and teacher outputs of the auxiliary classifiers.
1 code implementation • 5 Dec 2020 • Huan Wang, Suhas Lohit, Mike Jones, Yun Fu
What makes a "good" DA in KD?
no code implementations • NeurIPS 2020 • Zhiqiang Tao, Yaliang Li, Bolin Ding, Ce Zhang, Jingren Zhou, Yun Fu
Computing the gradient of model hyperparameters, i. e., hypergradient, enables a promising and natural way to solve the hyperparameter optimization task.
no code implementations • 14 Sep 2020 • Yue Bai, Zhiqiang Tao, Lichen Wang, Sheng Li, Yu Yin, Yun Fu
Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.
1 code implementation • ECCV 2020 • Shuhan Chen, Yun Fu
In this paper, we aim to develop an efficient and compact deep network for RGB-D salient object detection, where the depth image provides complementary information to boost performance in complex scenarios.
Ranked #11 on RGB-D Salient Object Detection on SIP
no code implementations • 28 Jul 2020 • Joseph P. Robinson, Zaid Khan, Yu Yin, Ming Shao, Yun Fu
Thus, to narrow the gap between research and reality and enhance the power of kinship recognition systems, we extend FIW with multimedia (MM) data (i. e., video, audio, and text captions).
1 code implementation • 29 Jun 2020 • Joseph P. Robinson, Ming Shao, Yun Fu
We review the public resources and data challenges that enabled and inspired many to hone-in on the views of automatic kinship recognition in the visual domain.
1 code implementation • NeurIPS 2020 • Yuchen Fan, Jiahui Yu, Yiqun Mei, Yulun Zhang, Yun Fu, Ding Liu, Thomas S. Huang
Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks.
no code implementations • CVPR 2020 • Gaurav Mittal, Chang Liu, Nikolaos Karianakis, Victor Fragoso, Mei Chen, Yun Fu
To reduce HPO time, we present HyperSTAR (System for Task Aware Hyperparameter Recommendation), a task-aware method to warm-start HPO for deep neural networks.
no code implementations • ICLR 2020 • Lichen Wang, Bo Zong, Qianqian Ma, Wei Cheng, Jingchao Ni, Wenchao Yu, Yanchi Liu, Dongjin Song, Haifeng Chen, Yun Fu
Inductive and unsupervised graph learning is a critical technique for predictive or information retrieval tasks where label information is difficult to obtain.
2 code implementations • 28 Apr 2020 • Yiqun Mei, Yuchen Fan, Yulun Zhang, Jiahui Yu, Yuqian Zhou, Ding Liu, Yun Fu, Thomas S. Huang, Humphrey Shi
Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales.
1 code implementation • 9 Apr 2020 • Jun Li, Hongfu Liu, Zhiqiang Tao, Handong Zhao, Yun Fu
This paper studies the large-scale subspace clustering (LSSC) problem with million data points.
1 code implementation • CVPR 2020 • Kai Li, Yulun Zhang, Kunpeng Li, Yun Fu
The recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data.
1 code implementation • CVPR 2020 • Kai Li, Curtis Wigington, Chris Tensmeyer, Handong Zhao, Nikolaos Barmpalios, Vlad I. Morariu, Varun Manjunatha, Tong Sun, Yun Fu
We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation.
no code implementations • 29 Mar 2020 • Qianqian Wang, Zhengming Ding, Zhiqiang Tao, Quanxue Gao, Yun Fu
Nowadays, with the rapid development of data collection sources and feature extraction methods, multi-view data are getting easy to obtain and have received increasing research attention in recent years, among which, multi-view clustering (MVC) forms a mainstream research direction and is widely used in data analysis.
3 code implementations • CVPR 2020 • Xiaoyu Xiang, Yapeng Tian, Yulun Zhang, Yun Fu, Jan P. Allebach, Chenliang Xu
Rather than synthesizing missing LR video frames as VFI networks do, we firstly temporally interpolate LR frame features in missing LR video frames capturing local temporal contexts by the proposed feature temporal interpolation network.
Ranked #4 on Video Frame Interpolation on Vid4 - 4x upscaling
Space-time Video Super-resolution Video Frame Interpolation +1
1 code implementation • 17 Feb 2020 • Yu Yin, Songyao Jiang, Joseph P. Robinson, Yun Fu
Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario.
1 code implementation • 16 Feb 2020 • Joseph P. Robinson, Gennady Livitz, Yann Henon, Can Qin, Yun Fu, Samson Timoner
Thus, the conventional approach of learning a global threshold for all pairs resulting in performance gaps among subgroups.
2 code implementations • 15 Feb 2020 • Joseph P. Robinson, Yu Yin, Zaid Khan, Ming Shao, Siyu Xia, Michael Stopa, Samson Timoner, Matthew A. Turk, Rama Chellappa, Yun Fu
Recognizing Families In the Wild (RFIW): an annual large-scale, multi-track automatic kinship recognition evaluation that supports various visual kin-based problems on scales much higher than ever before.
1 code implementation • 6 Feb 2020 • Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu
Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain.
1 code implementation • 4 Feb 2020 • Changyu Deng, Yizhou Wang, Can Qin, Yun Fu, Wei Lu
A small number of training data is generated dynamically based on the DNN's prediction of the optimum.
6 code implementations • IEEE Transactions on Image Processing 2020 • Shuhan Chen, Xiuli Tan, Ben Wang, Huchuan Lu, Xuelong Hu, Yun Fu
Benefiting from the quick development of deep convolutional neural networks, especially fully convolutional neural networks (FCNs), remarkable progresses have been achieved on salient object detection recently.
no code implementations • ECCV 2020 • Yulun Zhang, Zhifei Zhang, Stephen DiVerdi, Zhaowen Wang, Jose Echevarria, Yun Fu
We aim to super-resolve digital paintings, synthesizing realistic details from high-resolution reference painting materials for very large scaling factors (e. g., 8X, 16X).
no code implementations • 27 Nov 2019 • Gan Sun, Yang Cong, Qianqian Wang, Jun Li, Yun Fu
As a new spectral clustering task arrives, L2SC firstly transfers knowledge from both basis library and feature library to obtain encoding matrix, and further redefines the library base over time to maximize performance across all the clustering tasks.
no code implementations • 24 Nov 2019 • Yue Bai, Lichen Wang, Zhiqiang Tao, Sheng Li, Yun Fu
Multi-view time series classification (MVTSC) aims to improve the performance by fusing the distinctive temporal information from multiple views.
1 code implementation • 19 Nov 2019 • Yu Yin, Joseph P. Robinson, Yulun Zhang, Yun Fu
As for SR, the proposed method recovers sharper edges and more details from LR face images than other state-of-the-art methods, which we demonstrate qualitatively and quantitatively.
no code implementations • 16 Nov 2019 • Pengyu Gao, Siyu Xia, Joseph Robinson, Junkang Zhang, Chao Xia, Ming Shao, Yun Fu
Specifically, we propose a two-stage kin-face generation model to predict the appearance of a child given a pair of parents.
2 code implementations • NeurIPS 2019 • Can Qin, Haoxuan You, Lichen Wang, C. -C. Jay Kuo, Yun Fu
Specifically, most general-purpose DA methods that struggle for global feature alignment and ignore local geometric information are not suitable for 3D domain alignment.
Ranked #1 on Unsupervised Domain Adaptation on PreSIL to KITTI
no code implementations • 25 Oct 2019 • Bin Sun, Jun Li, Ming Shao, Yun Fu
To reduce the computation and memory costs, we propose a novel lightweight deep learning module by low-rank pointwise residual (LPR) convolution, called LPRNet.
no code implementations • 25 Oct 2019 • Bin Sun, Ming Shao, Siyu Xia, Yun Fu
To accelerate the model, we propose an efficient network structure to accelerate the evolutionary learning process through a factorization strategy.
no code implementations • 28 Sep 2019 • Zhengming Ding, Yandong Guo, Lei Zhang, Yun Fu
Specifically, we target at building a more effective general face classifier for both normal persons and one-shot persons.
1 code implementation • ICCV 2019 • Kai Li, Martin Renqiang Min, Yun Fu
We instead reformulate ZSL as a conditioned visual classification problem, i. e., classifying visual features based on the classifiers learned from the semantic descriptions.
2 code implementations • ICCV 2019 • Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu
It outperforms the current best method by 6. 8% relatively for image retrieval and 4. 8% relatively for caption retrieval on MS-COCO (Recall@1 using 1K test set).
Ranked #8 on Image Retrieval on Flickr30K 1K test
4 code implementations • CVPR 2019 • Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Yun Fu
We believe this is because of the combination of two factors: (a) the data imbalance between the old and new classes, and (b) the increasing number of visually similar classes.
1 code implementation • 7 May 2019 • Songyao Jiang, Hongfu Liu, Yue Wu, Yun Fu
Besides, a segmentor network is constructed to impose spatial constraints on the generator.
1 code implementation • 20 Apr 2019 • Lichen Wang, Bin Sun, Joseph Robinson, Taotao Jing, Yun Fu
To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities.
Ranked #4 on Multimodal Activity Recognition on EV-Action
2 code implementations • CVPR 2020 • Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, Yun Fu
Two head structures (i. e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks.
2 code implementations • ICCV 2019 • Yulun Zhang, Chen Fang, Yilin Wang, Zhaowen Wang, Zhe Lin, Yun Fu, Jimei Yang
An assumption widely used in recent neural style transfer methods is that image styles can be described by global statics of deep features like Gram or covariance matrices.
no code implementations • ICCV 2019 • Joseph P. Robinson, Yuncheng Li, Ning Zhang, Yun Fu, and Sergey Tulyakov
Our method claims state-of-the-art on all of the 300W benchmarks and ranks second-to-best on the Annotated Facial Landmarks in the Wild (AFLW) dataset.
Ranked #5 on Face Alignment on AFLW-19 (NME_box (%, Full) metric)
2 code implementations • ICLR 2019 • Yulun Zhang, Kunpeng Li, Kai Li, Bineng Zhong, Yun Fu
To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts.
no code implementations • 6 Mar 2019 • Gan Sun, Yang Cong, Qianqian Wang, Bineng Zhong, Yun Fu
Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e. g., knowledge library or deep network weights.
1 code implementation • 6 Jan 2019 • Songyao Jiang, Zhiqiang Tao, Yun Fu
Recently image-to-image translation has received increasing attention, which aims to map images in one domain to another specific one.
3 code implementations • 25 Dec 2018 • Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu
We fully exploit the hierarchical features from all the convolutional layers.
2 code implementations • 7 Dec 2018 • Yapeng Tian, Yulun Zhang, Yun Fu, Chenliang Xu
Video super-resolution (VSR) aims to restore a photo-realistic high-resolution (HR) video frame from both its corresponding low-resolution (LR) frame (reference frame) and multiple neighboring frames (supporting frames).
no code implementations • 19 Nov 2018 • Shuhui Jiang, Zhaowen Wang, Aaron Hertzmann, Hailin Jin, Yun Fu
Third, font pairing is an asymmetric problem in that the roles played by header and body fonts are not interchangeable.
3 code implementations • 8 Oct 2018 • Changsheng Lu, Siyu Xia, Ming Shao, Yun Fu
Over the years many ellipse detection algorithms spring up and are studied broadly, while the critical issue of detecting ellipses accurately and efficiently in real-world images remains a challenge.
no code implementations • 27 Sep 2018 • Guoshuai Zhao, Jun Li, Lu Wang, Xueming Qian, Yun Fu
In this paper, we propose a Graph-Sequence-to-Sequence(GraphSeq2Seq) model to fuse the dependency graph among words into the traditional Seq2Seq framework.
no code implementations • ECCV 2018 • Zhengming Ding, Sheng Li, Ming Shao, Yun Fu
However, existing approaches separate target label optimization and domain-invariant feature learning as different steps.
1 code implementation • 18 Aug 2018 • Kai Li, Zhengming Ding, Kunpeng Li, Yulun Zhang, Yun Fu
To ensure scalability and separability, a softmax-like function is formulated to push apart the positive and negative support sets.
20 code implementations • ECCV 2018 • Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, Yun Fu
To solve these problems, we propose the very deep residual channel attention networks (RCAN).
Ranked #15 on Image Super-Resolution on BSD100 - 4x upscaling
no code implementations • 28 Jun 2018 • Yu Kong, Yun Fu
Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state.
no code implementations • ICLR 2019 • Jun Li, Hongfu Liu, Bineng Zhong, Yue Wu, Yun Fu
To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS).
2 code implementations • CVPR 2018 • Kunpeng Li, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst, Yun Fu
Weakly supervised learning with only coarse labels can obtain visual explanations of deep neural network such as attention maps by back-propagating gradients.
16 code implementations • CVPR 2018 • Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu
In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers.
Ranked #3 on Color Image Denoising on CBSD68 sigma50
no code implementations • 2 Feb 2018 • Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Zhengyou Zhang, Yun Fu
To address these problems, we propose (a) a new loss function to combine the cross-entropy loss and distillation loss, (b) a simple way to estimate and remove the unbalance between the old and new classes , and (c) using Generative Adversarial Networks (GANs) to generate historical data and select representative exemplars during generation.
no code implementations • 5 Jan 2018 • Hongfu Liu, Jun Li, Yue Wu, Yun Fu
Then an objective function based Holoentropy is designed to enhance the compactness of each cluster with a few outliers removed.
no code implementations • NeurIPS 2017 • Sheng Li, Yun Fu
Estimating treatment effects from observational data is challenging due to the missing counterfactuals.
no code implementations • CVPR 2017 • Yu Kong, Zhiqiang Tao, Yun Fu
Different from after-the-fact action recognition, action prediction task requires action labels to be predicted from these partially observed videos.
no code implementations • CVPR 2017 • Zhengming Ding, Ming Shao, Yun Fu
Zero-shot learning for visual recognition has received much interest in the most recent years.
no code implementations • 7 Apr 2016 • Joseph P. Robinson, Ming Shao, Yue Wu, Yun Fu
Motivated by the lack of a single, unified dataset for kinship recognition, we aim to provide a dataset that captivates the interest of the research community.
no code implementations • ICCV 2015 • Sheng Li, Kang Li, Yun Fu
Subspace clustering is an effective technique for segmenting data drawn from multiple subspaces.
no code implementations • CVPR 2015 • Yu Kong, Yun Fu
Rich heterogeneous RGB and depth data are effectively compressed and projected to a learned shared space, in order to reduce noise and capture useful information for recognition.
no code implementations • NeurIPS 2012 • Chunxiao Zhou, Jiseong Park, Yun Fu
In this paper, a novel, computationally fast, and alternative algorithm for com- puting weighted v-statistics in resampling both univariate and multivariate data is proposed.