AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Adaptive Spatial-BCE Loss for Weakly Supervised Semantic Segmentation

Tong Wu, Guangyu Gao, Junshi Huang, Xiaolin Wei, Xiaoming Wei, Chi Harold Liu

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 44 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Spatial-BCE loss to the KL term (ablation)pseudo-label training · PASCAL VOC 2012 train pseudo-labels (phase 1)mIoU (%): 63.0 -> 64.2Improved
add Spatial-BCE loss to the KL term (ablation)pseudo-label training · PASCAL VOC 2012 train pseudo-labels (phase 2)mIoU (%): 63.7 -> 67.5Improved
determine threshold adaptively from predictions instead of fixed T/NT proportion (ablation)Spatial-BCE · PASCAL VOC 2012 train pseudo-labels (phase 2)mIoU (%): 60.5 -> 64.5Improved
determine threshold adaptively from predictions instead of fixed T/NT proportion (ablation)Spatial-BCE · PASCAL VOC 2012 train pseudo-labels (phase 1)mIoU (%): 59.7 -> 61.7Improved
iteratively update Qc for 3 phases (adaptive threshold) (ablation)Spatial-BCE · PASCAL VOC 2012 train pseudo-labelsmIoU (%): 53.0 -> 65.3Improved
iteratively update Qc for 3 phases (best threshold) (ablation)Spatial-BCE · PASCAL VOC 2012 train pseudo-labelsmIoU (%): 53.0 -> 68.1Improved
add dCRF to pseudo-labels after 3 phases (best threshold)Spatial-BCE · PASCAL VOC 2012 train pseudo-labelsmIoU (%): 68.1 -> 70.4Improved
add dCRF to pseudo-labels after 3 phases (adaptive threshold)Spatial-BCE · PASCAL VOC 2012 train pseudo-labelsmIoU (%): 65.3 -> 66.3Improved
add Qc update phase 1 to phase 3 (adaptive threshold) (ablation)Spatial-BCE · PASCAL VOC 2012 train pseudo-labelsmIoU (%): 61.7 -> 64.5 -> 65.3Improved
use saliency maps as post-processing in addition to image labelsSpatial-BCE · PASCAL VOC 2012 valmIoU (%): 70.0 -> 71.8Improved
use saliency maps as post-processing in addition to image labelsSpatial-BCE · MS-COCO 2014 valmIoU (%): 35.2 -> 38.6Improved
use Spatial-BCE pseudo-labels with best threshold instead of adaptiveSpatial-BCE · PASCAL VOC 2012 valmIoU (%): 68.5 -> 70.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy