Search Results for author: Siqi Hui

Found 4 papers, 3 papers with code

Semantic-aware Representation Learning for Homography Estimation

1 code implementation18 Jul 2024 YuHan Liu, Qianxin Huang, Siqi Hui, Jingwen Fu, Sanping Zhou, Kangyi Wu, Pengna Li, Jinjun Wang

In our work, we seek another way to use the semantic information, that is semantic-aware feature representation learning framework. Based on this, we propose SRMatcher, a new detector-free feature matching method, which encourages the network to learn integrated semantic feature representation. Specifically, to capture precise and rich semantics, we leverage the capabilities of recently popularized vision foundation models (VFMs) trained on extensive datasets.

Homography Estimation Representation Learning

Understanding the Overfitting of the Episodic Meta-training

no code implementations29 Jun 2023 Siqi Hui, Sanping Zhou, Ye Deng, Jinjun Wang

Specifically, we select the teacher model as the one with the best validation accuracy during meta-training and restrict the symmetric Kullback-Leibler (SKL) divergence between the output distribution of the linear classifier of the teacher model and that of the student model.

Knowledge Distillation

T-former: An Efficient Transformer for Image Inpainting

2 code implementations12 May 2023 Ye Deng, Siqi Hui, Sanping Zhou, Deyu Meng, Jinjun Wang

And based on this attention, a network called $T$-former is designed for image inpainting.

Image Inpainting Long-range modeling

Auxiliary Loss Reweighting for Image Inpainting

1 code implementation14 Nov 2021 Siqi Hui, Sanping Zhou, Ye Deng, Wenli Huang, Jinjun Wang

TPL and TSL are supersets of perceptual and style losses and release the auxiliary potential of standard perceptual and style losses.

Image Inpainting

Cannot find the paper you are looking for? You can Submit a new open access paper.