748 citations · 1.3k across the 20 of their papers we have counts for
20 papers
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
Runqi Wang, Xiaoyue Duan, Guoliang Kang +5
Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. Previous works adopt the conventional classification architecture, which…
PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation
Cilin Yan, Haochen Wang, Jie Liu +5
Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing. In such a task, target…
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
Gengwei Zhang, Liyuan Wang, Guoliang Kang +2
The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premis…
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Xiaoyue Duan, Guoliang Kang, Runqi Wang +4
Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a meta-model which may fast adapt to novel classes with only a few exemplars and meanwhile remain robust to a…
VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer
Mengshu Sun, Haoyu Ma, Guoliang Kang +5
The transformer architectures with attention mechanisms have obtained success in Nature Language Processing (NLP), and Vision Transformers (ViTs) have recently extended the applica…
Few-Shot Segmentation via Cycle-Consistent Transformer
Gengwei Zhang, Guoliang Kang, Yi Yang +1
Few-shot segmentation aims to train a segmentation model that can fast adapt to novel classes with few exemplars. The conventional training paradigm is to learn to make predictions…
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
Guoliang Kang, Yunchao Wei, Yi Yang +2
Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations. The conventi…
Training-free Monocular 3D Event Detection System for Traffic Surveillance
Lijun Yu, Peng Chen, Wenhe Liu +2
We focus on the problem of detecting traffic events in a surveillance scenario, including the detection of both vehicle actions and traffic collisions. Existing event detection sys…
Attract or Distract: Exploit the Margin of Open Set
Qianyu Feng, Guoliang Kang, Hehe Fan +1
Open set domain adaptation aims to diminish the domain shift across domains, with partially shared classes. There exist unknown target samples out of the knowledge of source domain…
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Chao Li, Zhiyuan Liu, Mengmeng Wu +7
Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves ca…
Shakeout: A New Approach to Regularized Deep Neural Network Training
Guoliang Kang, Jun Li, Dacheng Tao
Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural…
Contrastive Adaptation Network for Unsupervised Domain Adaptation
Guoliang Kang, Lu Jiang, Yi Yang +1
Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the do…
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
Yang He, Guoliang Kang, Xuanyi Dong +2
This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables th…
Self-produced Guidance for Weakly-supervised Object Localization
Xiaolin Zhang, Yunchao Wei, Guoliang Kang +2
Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discrimina…
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
Yang He, Xuanyi Dong, Guoliang Kang +3
Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has rec…
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
Guoliang Kang, Liang Zheng, Yan Yan +1
In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN). First, our approach transfers knowledge in all the co…
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
Weijian Deng, Liang Zheng, Qixiang Ye +3
Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the ba…
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
Xuanyi Dong, Guoliang Kang, Kun Zhan +1
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an ex…
Random Erasing Data Augmentation
Zhun Zhong, Liang Zheng, Guoliang Kang +2
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a recta…
PatchShuffle Regularization
Guoliang Kang, Xuanyi Dong, Liang Zheng +1
This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in an…