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

Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation

About

Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly complex designs at the cost of introducing more network components and additional training procedures. Differently, in this work, we follow a standard teacher-student framework and propose AugSeg, a simple and clean approach that focuses mainly on data perturbations to boost the SSS performance. We argue that various data augmentations should be adjusted to better adapt to the semi-supervised scenarios instead of directly applying these techniques from supervised learning. Specifically, we adopt a simplified intensity-based augmentation that selects a random number of data transformations with uniformly sampling distortion strengths from a continuous space. Based on the estimated confidence of the model on different unlabeled samples, we also randomly inject labelled information to augment the unlabeled samples in an adaptive manner. Without bells and whistles, our simple AugSeg can readily achieve new state-of-the-art performance on SSS benchmarks under different partition protocols.

Zhen Zhao, Lihe Yang, Sifan Long, Jimin Pi, Luping Zhou, Jingdong Wang• 2022

Related benchmarks

TaskDatasetResultRank
Semantic segmentationCityscapes (val)
mIoU80.43
287
Semantic segmentationPASCAL VOC classic 2012 (val)
mIoU81.36
143
Semantic segmentationPASCAL VOC 2012 (val)
mIoU81.5
126
Semantic segmentationPASCAL VOC augmented (val)
mIoU81.46
122
Medical Image SegmentationBUSI (test)
Dice72.03
121
Semantic segmentationPascal VOC (Original set)
mIoU81.4
105
Semantic segmentationPascal VOC blended 2012 (train)--
96
Semantic segmentationPASCAL VOC Augmented 2012
mIoU78.82
85
Semantic segmentationCityscapes 1/4 (744 labels)
mIoU79.6
80
Semantic segmentationCityscapes 1/16 (186 labeled samples)
mIoU75.22
68
Showing 10 of 50 rows

Other info

Code

Follow for update