7 citations · 21 across the 9 of their papers we have counts for
9 papers
A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification
Lei Qi, Lei Wang, Yinghuan Shi +1
Person re-identification (Re-ID) has achieved great success in the supervised scenario. However, it is difficult to directly transfer the supervised model to arbitrary unseen domai…
Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework
Lei Qi, Jiaqi Liu, Lei Wang +2
Domain generalization (DG) has attracted much attention in person re-identification (ReID) recently. It aims to make a model trained on multiple source domains generalize to an uns…
Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
Qian Yu, Lei Qi, Luping Zhou +5
Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these…
Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings
Wenbin Li, Xuesong Yang, Meihao Kong +4
Contrastive self-supervised learning (SSL) methods, such as MoCo and SimCLR, have achieved great success in unsupervised visual representation learning. They rely on a large number…
Asymmetric Distribution Measure for Few-shot Learning
Wenbin Li, Lei Wang, Jing Huo +3
The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings.…
Differentiable Meta-learning Model for Few-shot Semantic Segmentation
Pinzhuo Tian, Zhangkai Wu, Lei Qi +3
To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.…