conftrace_

feature suppression

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

contrastive learning (3) domain generalization (2) representation learning (2) salient token (1) simplicity bia (1) few-shot segmentation (1) instance discrimination (1) negative sampling (1) feature consistency (1) concept unlearning (1)

Papers

CRISP: Persistent Concept Unlearning via Sparse Autoencoders ACL 2026 Piercing the Fog: Disentangling Key Features for Vision Models in Multi-Degradation Scenarios AAAI 2026 Domain Generalization in CLIP via Learning with Diverse Text Prompts CVPR 2025 Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning ECCV 2024 START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation NeurIPS 2024 Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression ICML 2023 Intriguing Properties of Contrastive Losses NeurIPS 2021