AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery

Yuanpei Liu, Zhenqi He, Jialu Tang, Kai Han

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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 CloSeR (closed-set teacher + URD)SimGCD · Stanford-Cars (DINO)ACC All (%): 53.8 -> 63.0Improved
add CloSeRSelEx · CUB (DINO)ACC All (%): 73.6 -> 82.8Improved
add CloSeRSimGCD · fine-grained average (DINOv2)ACC New (%): 65.3 -> 74.5Improved
add CloSeRSimGCD · generic average (DINO)ACC All (%): 86.7 -> 88.8Improved
add CloSeRSimGCD · ImageNet-100 (DINOv2)ACC All (%): 89.9 -> 92.5Improved
add global relation distillation (ablation)SelEx · Stanford-Cars (DINO)ACC All (%): 58.5 -> 61.9Improved
add local relation distillation (ablation)SelEx · Stanford-Cars (DINO)ACC All (%): 58.5 -> 64.3Improved
combine global and local relations (ablation)SelEx · FGVC-Aircraft (DINO)ACC All (%): 59.0/63.0 -> 64.9Improved
add feature decoupling between global and local pathways (ablation)SelEx + URD · FGVC-Aircraft (DINO)ACC All (%): 64.9 -> 66.6Improved
add feature decoupling (ablation)SelEx + URD · Stanford-Cars (DINO)ACC All (%): 65.8 -> 66.5Improved
use block-wise adapter instead of fine-tuning only last block for the teacher (ablation)CloSeR teacher · Stanford-Cars (DINO)ACC All (%): 46.7 -> 63.0Improved
use block-wise adapter instead of full fine-tuning for the teacher (ablation)CloSeR teacher · CUB (DINO)ACC All (%): 68.1 -> 68.2No clear effect

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