57 citations · 58 across the 6 of their papers we have counts for
6 papers
FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learning
Siqi Hui, Sanping Zhou, Ye deng +2
Cross-domain few-shot learning (CD-FSL) aims to recognize novel classes with only a few labeled examples under significant domain shifts. While recent approaches leverage a limited…
Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack
Siqi Hui, Yiren Song, Sanping Zhou +3
Autoregressive (AR) image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent…
Semantic-aware Representation Learning for Homography Estimation
Yuhan Liu, Qianxin Huang, Siqi Hui +5
Homography estimation is the task of determining the transformation from an image pair. Our approach focuses on employing detector-free feature matching methods to address this iss…
Understanding the Overfitting of the Episodic Meta-training
Siqi Hui, Sanping Zhou, Ye deng +1
Despite the success of two-stage few-shot classification methods, in the episodic meta-training stage, the model suffers severe overfitting. We hypothesize that it is caused by ove…
T-former: An Efficient Transformer for Image Inpainting
Ye Deng, Siqi Hui, Sanping Zhou +2
Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of C…
Auxiliary Loss Reweighting for Image Inpainting
Siqi Hui, Sanping Zhou, Ye Deng +2
Image Inpainting is a task that aims to fill in missing regions of corrupted images with plausible contents. Recent inpainting methods have introduced perceptual and style losses a…