144 citations · 325 across the 12 of their papers we have counts for
12 papers
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Yujun Shi, Chuhui Xue, Jun Hao Liew +5
Accurate and controllable image editing is a challenging task that has attracted significant attention recently. Notably, DragGAN is an interactive point-based image editing framew…
Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Yuchao Gu, Xintao Wang, Jay Zhangjie Wu +10
Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new con…
Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning
Zeyin Song, Yifan Zhao, Yujun Shi +3
Few-shot class-incremental learning (FSCIL) aims at learning to classify new classes continually from limited samples without forgetting the old classes. The mainstream framework t…
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
Yujun Shi, Jian Liang, Wenqing Zhang +2
Federated learning aims to train models collaboratively across different clients without the sharing of data for privacy considerations. However, one major challenge for this learn…
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
Yujun Shi, Kuangqi Zhou, Jian Liang +5
Class Incremental Learning (CIL) aims at learning a multi-class classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Pre…
Refiner: Refining Self-attention for Vision Transformers
Daquan Zhou, Yujun Shi, Bingyi Kang +6
Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most…
Continual Learning via Bit-Level Information Preserving
Yujun Shi, Li Yuan, Yunpeng Chen +1
Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensi…
All Tokens Matter: Token Labeling for Training Better Vision Transformers
Zihang Jiang, Qibin Hou, Li Yuan +5
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViT…
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Li Yuan, Yunpeng Chen, Tao Wang +6
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT mo…
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric
Yujun Shi, Benben Liao, Guangyong Chen +3
The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). Despite many previous works studying the reason behind such ad…
Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Guangyong Chen, Pengfei Chen, Yujun Shi +3
In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can…
Learning Pixel-wise Labeling from the Internet without Human Interaction
Yun Liu, Yujun Shi, JiaWang Bian +3
Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samp…