5 citations · 24 across the 12 of their papers we have counts for
8 papers · 1 filter
ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection
Zhongzhan Huang, Pan Zhou, Shuicheng Yan +1
In diffusion models, UNet is the most popular network backbone, since its long skip connects (LSCs) to connect distant network blocks can aggregate long-distant information and all…
Understanding Self-attention Mechanism via Dynamical System Perspective
Zhongzhan Huang, Mingfu Liang, Jinghui Qin +2
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current ex…
Masked Images Are Counterfactual Samples for Robust Fine-tuning
Yao Xiao, Ziyi Tang, Pengxu Wei +2
Deep learning models are challenged by the distribution shift between the training data and test data. Recently, the large models pre-trained on diverse data have demonstrated unpr…
ASR: Attention-alike Structural Re-parameterization
Shanshan Zhong, Zhongzhan Huang, Wushao Wen +2
The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent param…
Open-World Pose Transfer via Sequential Test-Time Adaption
Junyang Chen, Xiaoyu Xian, Zhijing Yang +5
Pose transfer aims to transfer a given person into a specified posture, has recently attracted considerable attention. A typical pose transfer framework usually employs representat…
OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup
Zhijing Yang, Junyang Chen, Yukai Shi +3
Image Virtual try-on aims at replacing the cloth on a personal image with a garment image (in-shop clothes), which has attracted increasing attention from the multimedia and comput…
Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels
Tao Pu, Qianru Lao, Hefeng Wu +2
As a promising solution of reducing annotation cost, training multi-label models with partial positive labels (MLR-PPL), in which merely few positive labels are known while other a…
A Generic Shared Attention Mechanism for Various Backbone Neural Networks
Zhongzhan Huang, Senwei Liang, Mingfu Liang +1
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individua…