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.
Parameter-efficient fine-tuning for pre-trained vision models: A survey
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Introduces progressive task-specific multi-task adaptation for vision transformers, sharing adapters early and specializing later with gradient-based task allocation, outperforming prior methods on PASCAL and NYUD-v2 with fewer trainable parameters.
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT and KD methods on 18 tasks.
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.
-
Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Introduces progressive task-specific multi-task adaptation for vision transformers, sharing adapters early and specializing later with gradient-based task allocation, outperforming prior methods on PASCAL and NYUD-v2 with fewer trainable parameters.
-
Deep Reprogramming Distillation for Medical Foundation Models
DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT and KD methods on 18 tasks.