CUE mitigates concept confusion in long-tailed visual recognition by expanding supervision with multi-label concept sets from zero-shot CLIP and LLMs, using auxiliary Binary Logit-Adjustment losses to achieve stronger balanced performance than prior methods.
A simple long- tailed recognition baseline via vision-language model
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
BiasCareVL is a bias-aware vision-language framework trained on 3.44 million medical samples that outperforms prior methods on clinical tasks like diagnosis and segmentation while aiming for equitable performance under data imbalances.
citing papers explorer
-
CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning
CUE mitigates concept confusion in long-tailed visual recognition by expanding supervision with multi-label concept sets from zero-shot CLIP and LLMs, using auxiliary Binary Logit-Adjustment losses to achieve stronger balanced performance than prior methods.
-
Bias-constrained multimodal intelligence for equitable and reliable clinical AI
BiasCareVL is a bias-aware vision-language framework trained on 3.44 million medical samples that outperforms prior methods on clinical tasks like diagnosis and segmentation while aiming for equitable performance under data imbalances.