Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DMT: Dynamic Mutual Training for Semi-Supervised Learning

About

Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Self-training methods usually rely on single model prediction confidence to filter low-confidence pseudo labels, thus remaining high-confidence errors and wasting many low-confidence correct labels. In this paper, we point out it is difficult for a model to counter its own errors. Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors. With this new viewpoint, we propose mutual training between two different models by a dynamically re-weighted loss function, called Dynamic Mutual Training (DMT). We quantify inter-model disagreement by comparing predictions from two different models to dynamically re-weight loss in training, where a larger disagreement indicates a possible error and corresponds to a lower loss value. Extensive experiments show that DMT achieves state-of-the-art performance in both image classification and semantic segmentation. Our codes are released at https://github.com/voldemortX/DST-CBC .

Zhengyang Feng, Qianyu Zhou, Qiqi Gu, Xin Tan, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma• 2020

Related benchmarks

TaskDatasetResultRank
Semantic segmentationPASCAL VOC 2012 (val)
Mean IoU74.75
2040
Semantic segmentationGTA5 → Cityscapes (val)
mIoU63.2
533
Semantic segmentationPASCAL VOC (val)
mIoU74.8
338
Semantic segmentationCityscapes (val)
mIoU66.9
332
Semantic segmentationCityscapes (val)
mIoU68.2
133
Medical Image SegmentationKvasir-SEG (test)
mIoU79.32
78
Semantic segmentationSYNTHIA-to-Cityscapes 16 categories (val)
mIoU (Overall)59.7
74
Semantic segmentationCITYSCAPES 1/8 labeled samples 372 labels (val)
mIoU63
65
Image ClassificationCIFAR-10 4,000 labels (test)--
57
Semantic segmentationCityscapes fine (val)
mIoU68.16
42
Showing 10 of 17 rows

Other info

Code

Follow for update