AI Paper Atlas

Research map / Detection and segmentation / CNN features

SOLO: A Simple Framework for Instance Segmentation

Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li

TPAMI 2021 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 132 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 FPN multi-level prediction (pyramid) instead of single grid 24 (ablation)SOLO · COCO val2017mask AP: 29.0 -> 35.8Improved
add one CoordConv layer (ablation)SOLO · COCO val2017mask AP: 32.2 -> 35.8Improved
add more CoordConv layers (2 or 3 instead of 1) (ablation)SOLO · COCO val2017mask AP: 35.8 -> 35.7No clear effect
use Dice loss instead of focal loss (ablation)SOLO · COCO val2017mask AP: 31.6 -> 35.8Improved
use Dice loss instead of BCE (ablation)SOLO · COCO val2017mask AP: 30.0 -> 35.8Improved
replace BCE with Dice loss in Mask R-CNNMask R-CNN · COCOmask AP: -0.9Hurt
deepen head from 4 to 7 convs (ablation)SOLO · COCO val2017mask AP: 34.6 -> 35.8Improved
change category alignment method (interpolation, adaptive-pool, region-grid) (ablation)SOLO · COCOmask AP: +/-0.1% APNo clear effect
use decoupled SOLO instead of vanillaSOLO R50 · COCO test-devmask AP: 36.8 -> 37.4Improved
add explicit coordinates to kernel and feature branches (ablation)SOLOv2 R50 · COCO val2017mask AP: 36.3 -> 37.8Improved
use unified mask feature instead of separate (ablation)SOLOv2 R50 · COCO val2017mask AP: 37.3 -> 37.8Improved
use dynamic head instead of decoupled head (ablation)SOLOv2 · COCO val2017mask AP: 36.6 -> 37.3Improved

Earlier methods this paper compares with

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