AI Paper Atlas

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

Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation

Qi Fan, Lei Ke, Wenjie Pei, Chi-Keung Tang, Yu-Wing Tai

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 30 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 Boundary-Parsing Module (BM) (ablation)Baseline (ResNet-50) · COCO val voc->non-vocmask AP: 20.7 -> 27.4Improved
feed boundary feature to the mask head (FF) in BM (ablation)Baseline + BM · COCO val voc->non-vocmask AP: 21.6 -> 27.4Improved
add Non-local Affinity-Parsing Module (AM) (ablation)Baseline (ResNet-50) · COCO val voc->non-vocmask AP: 20.7 -> 27.2Improved
add affinity loss (AL) to AM (ablation)Baseline + AM · COCO val voc->non-vocmask AP: 26.9 -> 27.2Improved
add AM on top of BM (both modules) (ablation)Baseline + BM · COCO val voc->non-vocmask AP: 27.4 -> 28.8Improved
add BM on top of AM (ablation)Baseline + AM · COCO val voc->non-vocmask AP: 27.2 -> 28.8Improved
use CPMask instead of ShapeMaskShapeMask · COCO val voc->non-vocmask AP: 30.2 -> 34.0Improved
use CPMask instead of ShapeMaskShapeMask · COCO val non-voc->vocmask AP: 33.3 -> 36.8Improved
use CPMask instead of ShapeMask with NAS-FPNShapeMask (NAS-FPN) · COCO val voc->non-vocmask AP: 33.2 -> 34.0Improved
use CPMask instead of Meta R-CNNMeta R-CNN · COCO few-shot 10-shotmask AP: 4.4 -> 7.1Improved
use CPMask instead of Meta R-CNNMeta R-CNN · COCO few-shot 20-shotmask AP: 6.4 -> 10.3Improved
use FCOS-based CPMask instead of CenterMaskCenterMask · COCO test-dev fully supervisedmask AP: 38.3 -> 39.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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