AI Paper Atlas

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

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

Zhenzhen Weng, Mehmet Giray Ogut, Shai Limonchik, Serena Yeung

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 31 citations (OpenAlex)

Check 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
Use hierarchical self-supervised mask embeddings without long-tail box annotationsInstance segmentation trained with COCO masks · LVIS (COCO to LVIS)mAP: 0.056 -> 0.109Improved
Use hierarchical self-supervised mask embeddings without long-tail box annotationsInstance segmentation trained with VOC masks · COCO non-VOC categoriesmAP: 0.238 -> 0.327Improved
Initialize the mask proposal backbone with ImageNet pretraining rather than random initialization (ablation)Ours · LVIS (COCO to LVIS)mAP: 0.096 -> 0.109Improved
Increase proposals per image from 20 to 50 (ablation)Ours · LVISmAP: 0.0318 -> 0.1086Improved
Increase proposals per image from 50 to 100 (ablation)Ours · LVISmAP: 0.1086 -> 0.1083No clear effect
Set triplet-loss margin α to 0.2 rather than 0.1 (ablation)Ours · LVISmAP: 0.0806 -> 0.1086Improved
Increase triplet-loss margin α from 0.2 to 0.5 (ablation)Ours · LVISmAP: 0.1086 -> 0.0987Hurt
Set mask-loss weight β to 0.1 rather than 0.2 (ablation)Ours · LVISmAP: 0.1086 -> 0.0526Hurt
Set mask-loss weight β to 0.5 rather than 0.2 (ablation)Ours · LVISmAP: 0.1086 -> 0.0614Hurt
Add the mask loss to distinguish foreground from background (ablation)Ours · LVISmAP: 0.0689 -> 0.1086Improved
Add the object loss to bring overlapping proposals together and separate non-overlapping proposals (ablation)Ours · LVISmAP: 0.0374 -> 0.1086Improved
Add the hierarchical loss to encode parent-child relations (ablation)Ours · LVISmAP: 0.0846 -> 0.1086Improved

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