Dual-aware Domain Mining and Cross-aware Supervision for Weakly-supervised Semantic Segmentation
Open Access
- 4 May 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 17 (7) , 1-19
Abstract
Weakly Supervised Semantic Segmentation with image-level annotation uses localization maps from the classifier to generate pseudo labels. However, such localization maps focus only on sparse salient object regions, it is difficult to generate high-quality segmentation labels, which deviates from the requirement of semantic segmentation. To address this issue, we propose a dual-aware domain mining and cross-aware supervision (DDMCAS) method for weakly-supervised semantic segmentation. Specifically, we propose a dual-aware domain mining (DDM) module consisting of graph-based global reasoning unit and salient-region extension controller, which produces dense localization maps by exploring object features in salient regions and adjacent non-salient regions simultaneously. In order to further bridge the gap between salient regions and adjacent non-salient regions to generate more refined localization maps, we propose a cross-aware supervision (CAS) strategy to recover missing parts of the target objects and enhance weak attention in adjacent non-salient regions, leading to pseudo labels of higher quality for training the segmentation network. Based on the generated pseudo-labels, extensive experiments on PASCAL VOC 2012 dataset demonstrate that our method outperforms state-of-the-art methods using image-level labels for weakly supervised semantic segmentation.Keywords
Funding Information
- National Natural Science Foundation of China (62072463, 71531012)
- National Social Science Foundation of China (18ZDA309)
- Research Seed Funds of School of Interdisciplinary Studies of Renmin University of China
- Opening Project of State Key Laboratory of Digital Publishing Technology of Founder Group
This publication has 50 references indexed in Scilit:
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- STC: A Simple to Complex Framework for Weakly-Supervised Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation2016
- What’s the Point: Semantic Segmentation with Point Supervision2016
- Deep Residual Learning for Image Recognition2016
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation2016
- Learning Deep Features for Discriminative Localization2016
- Semantic Image Segmentation via Deep Parsing Network2015
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009