AI Paper Atlas

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

Bures Generalized Category Discovery

Luyao Tang, Kunze Huang, Chaoqi Chen, Cheng Chen

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory

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 BIA lossSimGCD · CUB (K given)All accuracy (%): 60.7 -> 62.1Improved
add BIA lossCMS · CUB (K given)All accuracy (%): 67.1 -> 71.1Improved
add BIA lossSelEx · CUB (K given)All accuracy (%): 78.7 -> 80.6Improved
add BIA lossSPTNet · FGVC Aircraft (K given)All accuracy (%): 51.6 -> 54.7Improved
add BIA lossSimGCD · ImageNet100 (K given)All accuracy (%): 83.3 -> 86.7Improved
add BIA lossSimGCD · CIFAR100 (K given)All accuracy (%): 80.1 -> 80.2No clear effect
add BIA lossCMS · CIFAR100 (K given)All accuracy (%): 79.5 -> 79.0Hurt
add BIA lossCMS · Herbarium 19 (K given)All accuracy (%): 36.5 -> 36.3No clear effect
add BIA loss on average over fine-grained datasetsGCD baselines · CUB (K given)average change in All accuracy: +2.2Improved
add BIA loss to estimate number of classesCMS · ImageNet100 K estimationerror rate (%): 2 -> 0Improved
add BIA loss to estimate number of classesCMS · Stanford Cars K estimationerror rate (%): 23.9 -> 18.9Improved
use BIA instead of VICReg as isotropy regularizer (ablation)CMS · CUB (isotropy comparison)All accuracy (%): 68.3 -> 71.1Improved

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