21 citations · 50 across the 6 of their papers we have counts for
7 papers
FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
Lihe Yang, Xiaogang Xu, Bingyi Kang +2
Semantic segmentation has witnessed tremendous progress due to the proposal of various advanced network architectures. However, they are extremely hungry for delicate annotations t…
Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Yijiang Li, Xinjiang Wang, Lihe Yang +3
Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, w…
Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning
Lihe Yang, Zhen Zhao, Lei Qi +3
Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly…
Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Zhen Zhao, Lihe Yang, Sifan Long +3
Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly co…
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
Lihe Yang, Lei Qi, Litong Feng +2
In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image ser…
ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
Lihe Yang, Wei Zhuo, Lei Qi +2
Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (n…
Mining Latent Classes for Few-shot Segmentation
Lihe Yang, Wei Zhuo, Lei Qi +2
Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e. potential novel clas…