Domain-Agnostic Prior for Transfer Semantic Segmentation

no code implementations • CVPR 2022 • Xinyue Huo, Lingxi Xie, Hengtong Hu, Wengang Zhou, Houqiang Li, Qi Tian

Unsupervised domain adaptation (UDA) is an important topic in the computer vision community.

Computer Vision Representation Learning +2

ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Image Segmentation

no code implementations • CVPR 2021 • Xinyue Huo, Lingxi Xie, Jianzhong He, Zijie Yang, Wengang Zhou, Houqiang Li, Qi Tian

Semi-supervised learning is a useful tool for image segmentation, mainly due to its ability in extracting knowledge from unlabeled data to assist learning from labeled data.

Continual Learning Self-Learning +1

Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations

no code implementations • 19 Nov 2020 • Xinyue Huo, Lingxi Xie, Longhui Wei, Xiaopeng Zhang, Hao Li, Zijie Yang, Wengang Zhou, Houqiang Li, Qi Tian

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation.

Contrastive Learning Data Augmentation +1

ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Medical Image Segmentation

no code implementations • 24 Jun 2020 • Xinyue Huo, Lingxi Xie, Jianzhong He, Zijie Yang, Qi Tian

This paper focuses on a popular pipeline known as self learning, and points out a weakness named lazy learning that refers to the difficulty for a model to learn from the pseudo labels generated by itself.

Autonomous Driving Self-Learning +2