AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Learning with Free Object Segments for Long-Tailed Instance Segmentation

Cheng Zhang, Tai-Yu Pan, Tianle Chen, Jike Zhong, Wenjin Fu, Wei-Lun Chao

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 13 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 free object segments pasted onto LVIS imagesMosaicOS, ResNet-50 · LVIS v1mask AP: 24.45 -> 25.19Improved
add free segments on top of calibrationMosaicOS, ResNet-50 · LVIS v1APr: 23.86 -> 25.11Improved
rank segments and keep top images (966K) instead of random 966K (ablation)free segments · LVIS v1mask AP: 24.50 -> 25.19Improved
rank images and keep 966K instead of using all 1,830K (ablation)free segments · LVIS v1mask AP: 24.87 -> 25.19Improved
use proposed ranking score instead of IoU (ablation)free segments · LVIS v1mask AP: 24.74 -> 25.19Improved
add drop-rate filtering of segments (ablation)free segments · LVIS v1mask AP: 24.81 -> 25.19Improved
paste segments onto LVIS images instead of training on object-centric images (ablation)free segments · LVIS v1mask AP: 24.78 -> 25.19Improved
add free segments to ground-truth copy-pasteMosaicOS · LVIS v1mask AP: 24.57 -> 25.36Improved
replace GT segment pasting with free segmentsMask R-CNN · LVIS v1mask AP: 24.06 -> 24.28Improved
add second training stage (ablation)free segments, Mask R-CNN · LVIS v1mask AP: 23.35 -> 24.28Improved
use free segments instead of self-training with LVIS networkMosaicOS · LVIS v1mask AP: 24.70 -> 25.19Improved
train 2x schedule instead of 1xMosaicOS w/ free segments · LVIS v1mask AP: 25.19 -> 26.80Improved

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