AI Paper Atlas

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

GloPER: Unsupervised Animal Pattern Extraction from Local Reconstruction

Bowen Chen, Yun Sing Koh, Gillian Dobbie

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 1 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
enforce local two-color reconstruction with Gumbel-Softmax masks (GloPER) instead of K-means/Watershed/SAM/CLIP-Seg/DINOunsupervised animal pattern segmentation · 10-species animal pattern datasetDICE: 42.44% higher DICE on average; best on all 10 speciesImproved
use GloPER-extracted binary patterns as ReID input instead of baseline masksDINO-based animal ReID · Animal ReIDRank-k accuracyImproved
use GloPER binary patterns instead of full RGB images for ReIDDINO-based animal ReID · Animal ReIDRank-k accuracyMixed
use a smaller kernel size (ablation)GloPER · Panda and GiraffeDICE and PIPMixed
use GloPER instead of baselines regarding fragmentationGloPER · 10-species animal pattern datasetPIPHurt

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