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

Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation

About

Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, namely Explicit Pseudo-pixel Supervision (EPS), which learns from pixel-level feedback by combining two weak supervisions; the image-level label provides the object identity via the localization map and the saliency map from the off-the-shelf saliency detection model offers rich boundaries. We devise a joint training strategy to fully utilize the complementary relationship between both information. Our method can obtain accurate object boundaries and discard co-occurring pixels, thereby significantly improving the quality of pseudo-masks. Experimental results show that the proposed method remarkably outperforms existing methods by resolving key challenges of WSSS and achieves the new state-of-the-art performance on both PASCAL VOC 2012 and MS COCO 2014 datasets.

Seungho Lee, Minhyun Lee, Jongwuk Lee, Hyunjung Shim• 2021

Related benchmarks

TaskDatasetResultRank
Semantic segmentationPASCAL VOC 2012 (val)
Mean IoU71
2040
Semantic segmentationPASCAL VOC 2012 (test)
mIoU71.8
1342
Semantic segmentationPASCAL VOC (val)
mIoU70.9
338
Semantic segmentationCOCO 2014 (val)
mIoU35.7
251
Semantic segmentationPascal VOC (test)
mIoU70.8
236
Weakly supervised semantic segmentationPASCAL VOC 2012 (test)--
158
Weakly supervised semantic segmentationPASCAL VOC 2012 (val)--
154
Semantic segmentationCOCO (val)
mIoU35.7
135
Semantic segmentationPASCAL VOC 2012 (train)
mIoU71.6
73
Semantic segmentationVOC 2012 (val)
mIoU70.9
67
Showing 10 of 18 rows

Other info

Code

Follow for update