Details

Autor(en) / Beteiligte

• Vedaldi, Andrea
• Bischof, Horst
• Brox, Thomas
• Frahm, Jan-Michael

Titel

Weakly Supervised Semantic Segmentation with Boundary Exploration

Ist Teil von

• Computer Vision - ECCV 2020, 2020, Vol.12371, p.347-362

Ort / Verlag

Switzerland: Springer International Publishing AG

Erscheinungsjahr

2020

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Weakly supervised semantic segmentation with image-level labels has attracted a lot of attention recently because these labels are already available in most datasets. To obtain semantic segmentation under weak supervision, this paper presents a simple yet effective approach based on the idea of explicitly exploring object boundaries from training images to keep coincidence of segmentation and boundaries. Specifically, we synthesize boundary annotations by exploiting coarse localization maps obtained from CNN classifier, and use annotations to train the proposed network called BENet which further excavates more object boundaries to provide constraints for segmentation. Finally generated pseudo annotations of training images are used to supervise an off-the-shelf segmentation network. We evaluate the proposed method on PASCAL VOC 2012 benchmark and the final results achieve 65.7% and 66.6% mIoU scores on val and test sets respectively, which outperforms previous methods trained under image-level supervision.