AI Paper Atlas

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

Weakly-Supervised Instance Segmentation via Class-Agnostic Learning With Salient Images

Xinggang Wang, Jiapei Feng, Bin Hu, Qi Ding, Longjin Ran, Xiaoxin Chen, Wenyu Liu

CVPR 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 36 citations (OpenAlex)

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
jointly train with salient imagesBoxCaseg on PASCAL VOC · PASCAL VOC 2012 valAP50: 58.9 -> 67.6Improved
use box-supervised class-agnostic learning with salient imagesWSIS on COCO · COCO test-devAP: 20.8 -> 30.9Improved
increase salient training images from 100 to all (ablation)BoxCaseg · PASCAL VOC 2012 valmIoU*: 61.8 -> 71.8Improved
add a weak segmentation head to the salient-only model (ablation)BoxCaseg · PASCAL VOC 2012 valmIoU*: 43.1 -> 70.5Improved
add a transferred segmentation head to the weak-head-only model (ablation)BoxCaseg · PASCAL VOC 2012 valmIoU*: 66.1 -> 69.7Improved
add the salient segmentation head to weak and transferred heads (ablation)BoxCaseg · PASCAL VOC 2012 valmIoU*: 69.7 -> 71.8Improved
use fixed-ratio batch sampling instead of random sampling (ablation)BoxCaseg · COCO valmIoU*: 58.1 -> 70.9Improved
use a 9:7 box-supervised-to-salient batch ratio (ablation)BoxCaseg · COCO valmIoU*: 70.7 -> 70.9Improved
combine salient and transferred segmentation head predictions (ablation)BoxCaseg · PASCAL VOC 2012 valmIoU*: 69.7 -> 71.8; 70.5 -> 71.8Improved
add smaller-object-better merging to proxy masks (ablation)Proxy Mask R-CNN · COCO valAP: 28.6 -> 29.5Improved
add proxy-box-agreement dropping after merging (ablation)Proxy Mask R-CNN · COCO valAP: 29.5 -> 30.9Improved
add proxy-box-agreement dropping after merging (ablation)Proxy Mask R-CNN · PASCAL VOC 2012 valAP: 40.2 -> 40.2No clear effect

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