AI Paper Atlas

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

CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning

Ruichi Zhang, Chikai Shang, Jiacheng Yang, Mengke Li, Yang Zhou, Junlong Gao, Yang Lu

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 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 VLM instance-level cue (ablation)LIFT (AdaptFormer + LA) · CIFAR100-LT (IR100)few-shot accuracy: 74.3 -> 81.6Improved
add LLM class-level cue (ablation)LIFT (AdaptFormer + LA) · CIFAR100-LT (IR100)few-shot accuracy: 74.3 -> 80.2Improved
add both VLM and LLM cues (ablation)LIFT (AdaptFormer + LA) · CIFAR100-LT (IR100)overall accuracy: 80.3 -> 82.8Improved
add both cues (ablation)LIFT · Places-LToverall accuracy: 51.5 -> 51.7Improved
add LLM cue to VLM cue (ablation)CUE · Places-LToverall accuracy: 51.6 -> 51.7No clear effect
add both cuesLIFT · ImageNet-LTfew-shot accuracy: 71.5 -> 73.0Improved
add CUELIFT · iNaturalist2018overall accuracy: 79.1 -> 79.6Improved
select VLM cue classes by top-k rather than random-k (ablation)CUE VLM cue · CIFAR100-LT (IR100)overall accuracy: 80.1 -> 82.8Improved
select VLM cue classes by top-k rather than last-k (ablation)CUE VLM cue · CIFAR100-LT (IR100)overall accuracy: 79.5 -> 82.8Improved
add CUE to VPT-shallowVPT-shallow · CIFAR100-LT (IR100)overall accuracy: 69.7 -> 76.5Improved
add CUE to LoRALoRA · CIFAR100-LT (IR100)overall accuracy: 79.1 -> 81.2Improved
add CUE to LOS trained from scratchLOS · CIFAR100-LT (IR100, from scratch)overall accuracy: 26.6 -> 31.9Improved

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