Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, 00, pp. 2623-2632
Issue Date:
2021-11-13
Filename Description Size
2103.14581.pdfPublished version2.09 MB
Adobe PDF
Full metadata record
Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However, existing works mainly concentrate on expanding the seed of pseudo labels within the image’s salient region. In this work, we propose a non-salient region object mining approach for weakly supervised semantic segmentation. We introduce a graph-based global reasoning unit to strengthen the classification network’s ability to capture global relations among disjoint and distant regions. This helps the network activate the object features outside the salient area. To further mine the non-salient region objects, we propose to exert the segmentation network’s self-correction ability. Specifically, a potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Moreover, we propose a non-salient region masking module for complex images to generate masked pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region. Extensive experiments on the PASCAL VOC dataset demonstrate state-of-the-art results compared to current methods. The source codes are available at https://github.com/NUST-Machine-Intelligence-Laboratory/nsrom.
Please use this identifier to cite or link to this item: