activity
20222024
most citedOn the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning

5 citations · 11 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG20241 cited

Towards Understanding Dual BN In Hybrid Adversarial Training

Chenshuang Zhang, Chaoning Zhang, Kang Zhang +3

There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples…

cs.CV2023

Multiple Object Tracking based on Occlusion-Aware Embedding Consistency Learning

Yaoqi Hu, Axi Niu, Yu Zhu +3

The Joint Detection and Embedding (JDE) framework has achieved remarkable progress for multiple object tracking. Existing methods often employ extracted embeddings to re-establish…

cs.CV20231 cited

Learning from Multi-Perception Features for Real-Word Image Super-resolution

Axi Niu, Kang Zhang, Trung X. Pham +4

Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-es…

cs.CV2023

GRAN: Ghost Residual Attention Network for Single Image Super Resolution

Axi Niu, Pei Wang, Yu Zhu +3

Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from hig…

eess.IV20232 cited

CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution

Axi Niu, Kang Zhang, Trung X. Pham +4

Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM to image super-resol…

cs.CV20225 cited

On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning

Trung Pham, Chaoning Zhang, Axi Niu +2

Exponential Moving Average (EMA or momentum) is widely used in modern self-supervised learning (SSL) approaches, such as MoCo, for enhancing performance. We demonstrate that such m…