Our new X account is live! Follow @wizwand_team for updates
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
2040
Semantic segmentationCityscapes (val)
mIoU66
572
Change DetectionLEVIR-CD (test)--
357
Semantic segmentationPASCAL VOC (val)
mIoU75.6
338
Semantic segmentationCityscapes (val)
mIoU66
332
Change DetectionWHU-CD (test)
IoU76.4
286
Semantic segmentationPascal VOC augmented 2012 (val)
mIoU74.5
162
Change DetectionWHU-CD
IoU76.4
133
Semantic segmentationCityscapes (val)
mIoU66
133
Semantic segmentationPASCAL VOC augmented (val)
mIoU73.2
122
Showing 10 of 37 rows

Other info

Follow for update