Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant
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.
Code (1)
Tasks
SegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationSimilar Papers 제목 키워드 기반
Learning Semi-Supervised Medical Image Segmentation from Spatial Registration
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+2Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer
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+2Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CT
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+2Robust Mutual Learning for Semi-supervised Semantic Segmentation
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 SegmentationAlternate Diverse Teaching for Semi-supervised Medical Image Segmentation
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