paper-with-me

홈 › Papers

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

2023-01-18 · NIPS 2022 11 · Ying Jin, Jiaqi Wang, Dahua Lin

Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data. To effectively leverage the unlabeled data, pseudo labeling, along with the teacher-student framework, is widely adopted in semi-supervised semantic segmentation. Though proved to be effective, this paradigm suffers from incorrect pseudo labels which inevitably exist and are taken as auxiliary training data. To alleviate the negative impact of incorrect pseudo labels, we delve into the current Semi-Supervised Semantic Segmentation frameworks. We argue that the unlabeled data with pseudo labels can facilitate the learning of representative features in the feature extractor, but it is unreliable to supervise the mask predictor. Motivated by this consideration, we propose a novel framework, Gentle Teaching Assistant (GTA-Seg) to disentangle the effects of pseudo labels on feature extractor and mask predictor of the student model. Specifically, in addition to the original teacher-student framework, our method introduces a teaching assistant network which directly learns from pseudo labels generated by the teacher network. The gentle teaching assistant (GTA) is coined gentle since it only transfers the beneficial feature representation knowledge in the feature extractor to the student model in an Exponential Moving Average (EMA) manner, protecting the student model from the negative influences caused by unreliable pseudo labels in the mask predictor. The student model is also supervised by reliable labeled data to train an accurate mask predictor, further facilitating feature representation. Extensive experiment results on benchmark datasets validate that our method shows competitive performance against previous methods. Code is available at https://github.com/Jin-Ying/GTA-Seg.

📄 PDF Abstract BibTeX arXiv:2301.07340

Code (1)

Jin-Ying/GTA-Seg 공식 구현 pytorch

Tasks

SegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Similar Papers 제목 키워드 기반

Learning Semi-Supervised Medical Image Segmentation from Spatial Registration

2024-09-16 · Qianying Liu, Paul Henderson, Xiao Gu, Hang Dai 외

Semi-supervised medical image segmentation has shown promise in training models with limited labeled data and abundant unlabeled data. However, state-of-the-art methods ignore a potentially valuable source of unsupervise…

Contrastive LearningImage SegmentationMedical Image SegmentationSegmentation+2

Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer

2021-12-09 · Xiangde Luo, Minhao Hu, Tao Song, Guotai Wang 외

Recently, deep learning with Convolutional Neural Networks (CNNs) and Transformers has shown encouraging results in fully supervised medical image segmentation. However, it is still challenging for them to achieve good p…

Image SegmentationMedical Image SegmentationPseudo LabelSegmentation+2

Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CT

2022-11-11 · Jae Won Choi

For more clinical applications of deep learning models for medical image segmentation, high demands on labeled data and computational resources must be addressed. This study proposes a coarse-to-fine framework with two t…

Image SegmentationKnowledge DistillationMedical Image SegmentationOrgan Segmentation+2

Robust Mutual Learning for Semi-supervised Semantic Segmentation

2021-06-01 · Pan Zhang, Bo Zhang, Ting Zhang, Dong Chen 외

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppr…

Pseudo LabelSemantic SegmentationSemi-Supervised Semantic Segmentation

Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation

2023-11-29 · Zhen Zhao, Zicheng Wang, Longyue Wang, Dian Yu 외

Semi-supervised medical image segmentation studies have shown promise in training models with limited labeled data. However, current dominant teacher-student based approaches can suffer from the confirmation bias. To add…

Data AugmentationImage SegmentationMedical Image SegmentationSemantic Segmentation+1