70 citations · 341 across the 32 of their papers we have counts for
33 papers
Structured Cooperative Learning with Graphical Model Priors
Shuangtong Li, Tianyi Zhou, Xinmei Tian +1
We study how to train personalized models for different tasks on decentralized devices with limited local data. We propose "Structured Cooperative Learning (SCooL)", in which a coo…
Moderately Distributional Exploration for Domain Generalization
Rui Dai, Yonggang Zhang, Zhen Fang +2
Domain generalization (DG) aims to tackle the distribution shift between training domains and unknown target domains. Generating new domains is one of the most effective approaches…
Semantic-Aware Mixup for Domain Generalization
Chengchao Xu, Xinmei Tian
Deep neural networks (DNNs) have shown exciting performance in various tasks, yet suffer generalization failures when meeting unknown target domains. One of the most promising appr…
On Efficient Training of Large-Scale Deep Learning Models: A Literature Review
Li Shen, Yan Sun, Zhiyuan Yu +3
The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech. The use of large-scale models tr…
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
Kaiwen Yang, Yanchao Sun, Jiahao Su +5
Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on auto…
Towards Lightweight Black-Box Attacks against Deep Neural Networks
Chenghao Sun, Yonggang Zhang, Wan Chaoqun +5
Black-box attacks can generate adversarial examples without accessing the parameters of target model, largely exacerbating the threats of deployed deep neural networks (DNNs). Howe…
Self-Supervision Can Be a Good Few-Shot Learner
Yuning Lu, Liangjian Wen, Jianzhuang Liu +2
Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic p…
Bi-Calibration Networks for Weakly-Supervised Video Representation Learning
Fuchen Long, Ting Yao, Zhaofan Qiu +3
The leverage of large volumes of web videos paired with the searched queries or surrounding texts (e.g., title) offers an economic and extensible alternative to supervised video re…
Toward Real-world Single Image Deraining: A New Benchmark and Beyond
Wei Li, Qiming Zhang, Jing Zhang +3
Single image deraining (SID) in real scenarios attracts increasing attention in recent years. Due to the difficulty in obtaining real-world rainy/clean image pairs, previous real d…
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
Rong Dai, Li Shen, Fengxiang He +2
Personalized federated learning is proposed to handle the data heterogeneity problem amongst clients by learning dedicated tailored local models for each user. However, existing wo…
QAOA-in-QAOA: solving large-scale MaxCut problems on small quantum machines
Zeqiao Zhou, Yuxuan Du, Xinmei Tian +1
The design of fast algorithms for combinatorial optimization greatly contributes to a plethora of domains such as logistics, finance, and chemistry. Quantum approximate optimizatio…
Prompt Distribution Learning
Yuning Lu, Jianzhuang Liu, Yonggang Zhang +2
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias pr…
A Style and Semantic Memory Mechanism for Domain Generalization
Yang Chen, Yu Wang, Yingwei Pan +3
Mainstream state-of-the-art domain generalization algorithms tend to prioritize the assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain style inv…
Transferrable Contrastive Learning for Visual Domain Adaptation
Yang Chen, Yingwei Pan, Yu Wang +3
Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorpo…
Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
Zhen Huang, Xu Shen, Jun Xing +6
Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged…
Domain-Class Correlation Decomposition for Generalizable Person Re-Identification
Kaiwen Yang, Xinmei Tian
Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to…
CausalAdv: Adversarial Robustness through the Lens of Causality
Yonggang Zhang, Mingming Gong, Tongliang Liu +5
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning. As causal reasoning has an instinct for modelling distribution change…
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
Zhen Huang, Xu Shen, Xinmei Tian +3
Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely…
Learning to Localize Actions from Moments
Fuchen Long, Ting Yao, Zhaofan Qiu +3
With the knowledge of action moments (i.e., trimmed video clips that each contains an action instance), humans could routinely localize an action temporally in an untrimmed video.…
Transform-Invariant Convolutional Neural Networks for Image Classification and Search
Xu Shen, Xinmei Tian, Anfeng He +2
Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invaria…
Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks
Xu Shen, Xinmei Tian, Shaoyan Sun +1
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations…
Continuous Dropout
Xu Shen, Xinmei Tian, Tongliang Liu +2
Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detect…
Quantization Networks
Jiwei Yang, Xu Shen, Jun Xing +5
Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit q…
Gaussian Temporal Awareness Networks for Action Localization
Fuchen Long, Ting Yao, Zhaofan Qiu +3
Temporally localizing actions in a video is a fundamental challenge in video understanding. Most existing approaches have often drawn inspiration from image object detection and ex…