AI Paper Atlas

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

ECS-Net: Improving Weakly Supervised Semantic Segmentation by Using Connections Between Class Activation Maps

Kunyang Sun, Haoqing Shi, Zhengming Zhang, Yongming Huang

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 135 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 erasing of discriminative regions without connections between CAMs (ablation)CAM baseline · VOC 2012 trainmIoU: 47.4 -> 48.5Improved
add segment supervision from connections between original and erased CAMs (CE loss) (ablation)ECS-Net · VOC 2012 trainmIoU: 48.5 -> 55.1Improved
add other improvements (0.5 0.8 model, multi dilated overlay module) (ablation)ECS-Net · VOC 2012 trainmIoU: 55.1 -> 56.6Improved
add CRF post-processing (ablation)ECS-Net · VOC 2012 trainmIoU: 56.6 -> 58.6Improved
use rescale factor 0.5 instead of 1 for first input image (ablation)ECS-Net · VOC 2012 trainmIoU: 55.1 -> 56.1Improved
use rescale factor 0.7 instead of 1 for first input image (ablation)ECS-Net · VOC 2012 trainmIoU: 55.1 -> 55.7Improved
raise threshold theta from 0.6 to 0.8 (ablation)ECS-Net · VOC 2012 trainmIoU: 53.8 -> 55.1Improved
raise threshold theta from 0.8 to 0.9 (ablation)ECS-Net · VOC 2012 trainmIoU: 55.1 -> 54.9Hurt
use CAM heatmap H' rather than refine heatmap E' to produce segment labels (ablation)ECS-Net · VOC 2012 trainmIoU: 54.2 -> 55.1Improved
use ECS-Net CAMs instead of SEAM-refined CAMsCAM · VOC 2012 trainmIoU: 55.4 -> 56.6Improved
use ECS-Net pseudo labels with ResNet-38 instead of SEAMDeepLabv1 · VOC 2012 valmIoU: 64.5 -> 66.6Improved

Later papers that compared with this method

1 later accepted paper reports ECS-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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