no code implementations • ECCV 2020 • Xiaoyu Tao, Xinyuan Chang, Xiaopeng Hong, Xing Wei, Yihong Gong
A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network's recognition performance on old classes degrades severely when incrementally learning new classes.
no code implementations • 21 Apr 2024 • Songlin Dong, Yingjie Chen, Yuhang He, Yuhan Jin, Alex C. Kot, Yihong Gong
Online task-free continual learning (OTFCL) is a more challenging variant of continual learning which emphasizes the gradual shift of task boundaries and learns in an online mode.
no code implementations • 27 Mar 2024 • Shenxing Wei, Xing Wei, Zhiheng Ma, Songlin Dong, Shaochen Zhang, Yihong Gong
Recent research in this domain has emphasized the necessity of a large volume of training data, overlooking the practical scenario where, post-deployment of the model, unlabeled data containing both normal and abnormal samples can be utilized to enhance the model's performance.
no code implementations • 11 Mar 2024 • Xinyuan Gao, Songlin Dong, Yuhang He, Xing Wei, Yihong Gong
Besides, to address the classifier bias towards the new classes, we propose a novel approach to generate the pseudo-features to correct the classifier.
1 code implementation • 28 Dec 2023 • Yifan Bai, Zeyang Zhao, Yihong Gong, Xing Wei
We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames.
Ranked #1 on Visual Object Tracking on NeedForSpeed
1 code implementation • ICCV 2023 • Songlin Dong, Haoyu Luo, Yuhang He, Xing Wei, Yihong Gong
Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied.
no code implementations • CVPR 2023 • Xinyuan Gao, Yuhang He, Songlin Dong, Jie Cheng, Xing Wei, Yihong Gong
Deep neural networks suffer from catastrophic forgetting in class incremental learning, where the classification accuracy of old classes drastically deteriorates when the networks learn the knowledge of new classes.
1 code implementation • CVPR 2023 2023 • Xing Wei, Yifan Bai, Yongchao Zheng, Dahu Shi, Yihong Gong
We present ARTrack, an autoregressive framework for visual object tracking.
Ranked #1 on Visual Tracking on TNL2K
no code implementations • 11 Mar 2022 • Xiaohan Zhang, Songlin Dong, Jinjie Chen, Qi Tian, Yihong Gong, Xiaopeng Hong
In this paper, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories.
no code implementations • 31 Dec 2021 • Xing Wei, Yuanrui Kang, Jihao Yang, Yunfeng Qiu, Dahu Shi, Wenming Tan, Yihong Gong
First of all, we design a deformable attention in-built Transformer backbone, which learns adaptive feature representations with deformable sampling locations and dynamic attention weights.
1 code implementation • 4 Nov 2021 • Muhammad Rifki Kurniawan, Xing Wei, Yihong Gong
Online continual learning in the wild is a very difficult task in machine learning.
no code implementations • IEEE International Conference on Image Processing (ICIP) 2021 • Jiawei Ma, Xiaoyu Tao, Jianxing Ma, Xiaopeng Hong, Yihong Gong
Class Incremental Learning (CIL) is a hot topic in machine learning for CNN models to learn new classes incrementally.
1 code implementation • 21 Jul 2021 • Ning li, Kaitao Jiang, Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong
Anomaly detection plays a key role in industrial manufacturing for product quality control.
Ranked #46 on Anomaly Detection on MVTec AD
no code implementations • 4 Jul 2021 • Hui Lin, Xiaopeng Hong, Zhiheng Ma, Xing Wei, Yunfeng Qiu, YaoWei Wang, Yihong Gong
Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.
no code implementations • 31 May 2021 • Yuhang He, Wentao Yu, Jie Han, Xing Wei, Xiaopeng Hong, Yihong Gong
In this paper, we focus on the multi-object tracking (MOT) problem of automatic driving and robot navigation.
no code implementations • ICCV 2021 • Zhiheng Ma, Xiaopeng Hong, Xing Wei, Yunfeng Qiu, Yihong Gong
This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets.
1 code implementation • CVPR 2020 • Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, Yihong Gong
FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones.
Ranked #8 on Few-Shot Class-Incremental Learning on CIFAR-100 (Average Accuracy metric)
no code implementations • 30 Oct 2019 • Wenjie Ding, Xing Wei, Rongrong Ji, Xiaopeng Hong, Qi Tian, Yihong Gong
We propose a \emph{more universal} adversarial perturbation (MUAP) method for both image-agnostic and model-insensitive person Re-ID attack.
3 code implementations • ICCV 2019 • Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong
In crowd counting datasets, each person is annotated by a point, which is usually the center of the head.
no code implementations • ECCV 2018 • Weiwei Shi, Yihong Gong, Chris Ding, Zhiheng MaXiaoyu Tao, Nanning Zheng
In this paper, we propose Transductive Semi-Supervised Deep Learning (TSSDL) method that is effective for training Deep Convolutional Neural Network (DCNN) models.
no code implementations • ECCV 2018 • Xing Wei, Yue Zhang, Yihong Gong, Jiawei Zhang, Nanning Zheng
The reason is that the bilinear feature matrix is sensitive to the magnitudes and correlations of local CNN feature elements which can be measured by its singular values.
Fine-Grained Image Classification Fine-Grained Visual Recognition +1
no code implementations • 4 Jul 2018 • Sanping Zhou, Jinjun Wang, Deyu Meng, Yudong Liang, Yihong Gong, Nanning Zheng
Specifically, a novel foreground attentive subnetwork is designed to drive the network's attention, in which a decoder network is used to reconstruct the binary mask by using a novel local regression loss function, and an encoder network is regularized by the decoder network to focus its attention on the foreground persons.
no code implementations • CVPR 2018 • Xing Wei, Yue Zhang, Yihong Gong, Nanning Zheng
Experimental results on several patch matching benchmarks show that our method outperforms the state-of-the-arts significantly.
no code implementations • NeurIPS 2017 • Bo Jiang, Jin Tang, Chris Ding, Yihong Gong, Bin Luo
As a fundamental problem in computer vision, graph matching problem can usually be formulated as a Quadratic Programming (QP) problem with doubly stochastic and discrete (integer) constraints.
no code implementations • 7 Oct 2017 • Sanping Zhou, Jinjun Wang, Deyu Meng, Xiaomeng Xin, Yubing Li, Yihong Gong, Nanning Zheng
In this paper, we propose a novel deep self-paced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to help the relative distance metric training the deep neural network, so as to learn the stable and discriminative features for person Re-ID.
2 code implementations • 5 Oct 2017 • Shun Zhang, Jia-Bin Huang, Jongwoo Lim, Yihong Gong, Jinjun Wang, Narendra Ahuja, Ming-Hsuan Yang
Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up.
no code implementations • 18 Aug 2017 • Sanping Zhou, Jinjun Wang, Rui Shi, Qiqi Hou, Yihong Gong, Nanning Zheng
The class-identity term keeps the intra-class samples within each camera view gathering together, the relative distance term maximizes the distance between the intra-class class set and inter-class set across different camera views, and the regularization term smoothness the parameters of deep convolutional neural network (CNN).
no code implementations • 25 Jul 2017 • De Cheng, Yihong Gong, Zhihui Li, Weiwei Shi, Alexander G. Hauptmann, Nanning Zheng
The proposed method can take full advantages of the structured distance relationships among these training samples, with the constructed complete graph.
no code implementations • CVPR 2017 • Sanping Zhou, Jinjun Wang, Jiayun Wang, Yihong Gong, Nanning Zheng
One of the key issues for deep learning based person Re-ID is the selection of proper similarity comparison criteria, and the performance of learned features using existing criterion based on pairwise similarity is still limited, because only P2P distances are mostly considered.
no code implementations • 31 Mar 2017 • Yudong Liang, Radu Timofte, Jinjun Wang, Yihong Gong, Nanning Zheng
The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors.
no code implementations • CVPR 2016 • De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, Nanning Zheng
Person re-identification across cameras remains a very challenging problem, especially when there are no overlapping fields of view between cameras.
1 code implementation • 20 May 2016 • Xing Wei, Qingxiong Yang, Yihong Gong, Ming-Hsuan Yang, Narendra Ahuja
Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.
no code implementations • 23 Mar 2016 • Amir Shahroudy, Tian-Tsong Ng, Yihong Gong, Gang Wang
Single modality action recognition on RGB or depth sequences has been extensively explored recently.
no code implementations • CVPR 2013 • Huaizu Jiang, Zejian yuan, Ming-Ming Cheng, Yihong Gong, Nanning Zheng, Jingdong Wang
Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score.
no code implementations • NeurIPS 2011 • Zhen Li, Huazhong Ning, Liangliang Cao, Tong Zhang, Yihong Gong, Thomas S. Huang
Traditional approaches relied on algorithmic constructions that are often data independent (such as Locality Sensitive Hashing) or weakly dependent (such as kd-trees, k-means trees).
no code implementations • NeurIPS 2009 • Kai Yu, Tong Zhang, Yihong Gong
This paper introduces a new method for semi-supervised learning on high dimensional nonlinear manifolds, which includes a phase of unsupervised basis learning and a phase of supervised function learning.
no code implementations • NeurIPS 2008 • Shenghuo Zhu, Kai Yu, Yihong Gong
Stochastic relational models provide a rich family of choices for learning and predicting dyadic data between two sets of entities.
no code implementations • NeurIPS 2008 • Kai Yu, Wei Xu, Yihong Gong
In this paper we focus on training deep neural networks for visual recognition tasks.
no code implementations • NeurIPS 2007 • Shenghuo Zhu, Kai Yu, Yihong Gong
It is becoming increasingly important to learn from a partially-observed random matrix and predict its missing elements.