Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression

25 May 2023

Papers citing "Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression"

9 / 9 papers shown

Title
Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation Jiawen Xu O. Kao Margret Keuper 0 0 0 19 May 2025
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Sanghwan Kim Rui Xiao Mariana-Iuliana Georgescu Stephan Alaniz Zeynep Akata VLM 85 2 0 02 Dec 2024
CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning Junghun Oh Sungyong Baik Kyoung Mu Lee CLL 34 3 0 08 Oct 2024
Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networks S. Joshi Jiayi Ni Baharan Mirzasoleiman DD 72 2 0 03 Oct 2024
Learned feature representations are biased by complexity, learning order, position, and more Andrew Kyle Lampinen Stephanie C. Y. Chan Katherine Hermann AI4CE FaML SSL OOD 37 6 0 09 May 2024
Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations GuanWen Qiu Da Kuang Surbhi Goel 27 8 0 05 Mar 2024
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training Cong Fang Hangfeng He Qi Long Weijie J. Su FAtt 130 165 0 29 Jan 2021
An Investigation of Why Overparameterization Exacerbates Spurious Correlations Shiori Sagawa Aditi Raghunathan Pang Wei Koh Percy Liang 152 371 0 09 May 2020
Convolutional Neural Networks Analyzed via Convolutional Sparse Coding Vardan Papyan Yaniv Romano Michael Elad 59 284 0 27 Jul 2016