Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

About

The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification with limited data has only drawn attention recently. In this work, we propose an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images. It uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The dual-branch approach reduces both the low-level and the high-level artifacts typical when training with few labels. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks - PASCAL VOC 2012, PASCAL-Context, and Cityscapes - the approach achieves new state-of-the-art in semi-supervised learning.

Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox• 2019

Related benchmarks

TaskDatasetResultRank
Semantic segmentationPASCAL VOC 2012 (val)
Mean IoU75.6
2142
Semantic segmentationCityscapes (val)
mIoU66
572
Change DetectionLEVIR-CD (test)--
485
Semantic segmentationCityscapes (val)
mIoU66
374
Change DetectionWHU-CD (test)
IoU76.4
372
Semantic segmentationPASCAL VOC (val)
mIoU75.6
362
Change DetectionWHU-CD
IoU76.4
202
Semantic segmentationPascal VOC augmented 2012 (val)
mIoU74.5
162
Semantic segmentationCityscapes (val)
mIoU66
133
Semantic segmentationPASCAL VOC augmented (val)
mIoU73.2
122
Showing 10 of 37 rows

Other info

Follow for update