AI Paper Atlas

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

Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation

Junsong Fan, Zhaoxiang Zhang, Tieniu Tan

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 62 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
train on a second noisy label set instead of one (noise ratio 0.3) (ablation)VGG16-LargeFov · VOC 2012 val (hand-crafted noise)mIoU (%): 64.8 -> 66.2Improved
add CRF seeds to threshold seeds (multi-type) (ablation)VGG16 CAM seeds · VOC 2012 valmIoU (%): 61.4 -> 63.8Improved
use threshold plus CRF seeds from RES38 CAM (ablation)RES38 CAM seeds · VOC 2012 valmIoU (%): 62.3 -> 63.5Improved
use three CAM scales as separate seeds (ablation)threshold seeds · VOC 2012 valmIoU (%): 61.4 -> 62.5Improved
use three CAM scales as separate seeds (ablation)both seed types · VOC 2012 valmIoU (%): 63.8 -> 64.0Improved
merge multi-scale CAMs into one seed set by max fusion instead of separate seeds (ablation)threshold seeds · VOC 2012 valmIoU (%): 62.5 -> 60.2Hurt
use separate multi-scale seeds instead of average-fused seeds (ablation)both seed types · VOC 2012 valmIoU (%): 63.9 -> 64.0Improved
add RES38 seeds to VGG16 seeds (ablation)both seed types · VOC 2012 valmIoU (%): 63.8 -> 64.2Improved
add RES38 seeds to VGG16 seeds (ablation)CRF seeds · VOC 2012 valmIoU (%): 62.9 -> 63.1Improved
add weighted selective training with all three seed kinds (ablation)multi-type, multi-scale, multi-arch seeds · VOC 2012 valmIoU (%): 63.9 -> 64.6Improved
add weighted selective training with multi-type seeds only (ablation)multi-type seeds · VOC 2012 valmIoU (%): 63.9 -> 63.8No clear effect
add weighted selective training to multi-type and multi-scale seeds (ablation)multi-type, multi-scale seeds · VOC 2012 valmIoU (%): 63.8 -> 64.0Improved

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