AI Paper Atlas

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

Leveraging Auxiliary Tasks With Affinity Learning for Weakly Supervised Semantic Segmentation

Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel, Dan Xu

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 183 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 multi-label image classification auxiliary task (ablation)segmentation baseline · PASCAL VOC 2012 valmIoU (%): 56.9 -> 57.6Improved
add saliency detection auxiliary task (ablation)segmentation baseline · PASCAL VOC 2012 valmIoU (%): 56.9 -> 59.8Improved
add both classification and saliency auxiliary tasks (ablation)segmentation baseline · PASCAL VOC 2012 valmIoU (%): 56.9 -> 60.8Improved
add segmentation-only affinity learning (ablation)AuxSegNet multi-task baseline · PASCAL VOC 2012 valmIoU (%): 60.8 -> 61.5Improved
use cross-task affinity instead of segmentation-only affinity (ablation)AuxSegNet · PASCAL VOC 2012 valmIoU (%): 61.5 -> 62.6Improved
add saliency constraint on cross-task affinity (ablation)AuxSegNet · PASCAL VOC 2012 valmIoU (%): 62.6 -> 64.1Improved
iterative pseudo-label updating over stages (ablation)AuxSegNet · PASCAL VOC 2012 valmIoU (%): 64.1 -> 66.1Improved
refine CAM with cross-task affinity in first label update (ablation)AuxSegNet pseudo labels · PASCAL VOC 2012 train (pseudo labels)precision/recall/mIoU (%): recall 42.9 -> +8.9, mIoU 40.6 -> +8.6Improved
add CRF post-processing and multi-scale testing (ablation)AuxSegNet · PASCAL VOC 2012 valmIoU (%): 66.1 -> 69.0Improved
swap pre-trained saliency model to Zhang et al. (weakly supervised) (ablation)AuxSegNet · PASCAL VOC 2012 val (pre-trained saliency model comparison)mIoU (%): 53.0 -> 66.5Improved
swap pre-trained saliency model to PoolNet (ablation)AuxSegNet · PASCAL VOC 2012 val (pre-trained saliency model comparison)mIoU (%): 55.7 -> 68.4Improved
swap pre-trained saliency model to MINet (ablation)AuxSegNet · PASCAL VOC 2012 val (pre-trained saliency model comparison)mIoU (%): 55.8 -> 68.9Improved

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