paper-with-me

홈 › Papers

Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation

2024-02-22 · Jamshid Hassanpour, Vinkle Srivastav, Didier Mutter, Nicolas Padoy

Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive learning, which involves forming pairs of similar and dissimilar input samples, guiding the model to distinguish between them. In this work, we investigate the application of contrastive learning to the domain of medical image analysis. Our findings reveal that MoCo v2, a state-of-the-art contrastive learning method, encounters dimensional collapse when applied to medical images. This is attributed to the high degree of inter-image similarity shared between the medical images. To address this, we propose two key contributions: local feature learning and feature decorrelation. Local feature learning improves the ability of the model to focus on the local regions of the image, while feature decorrelation removes the linear dependence among the features. Our experimental findings demonstrate that our contributions significantly enhance the model's performance in the downstream task of medical segmentation, both in the linear evaluation and full fine-tuning settings. This work illustrates the importance of effectively adapting SSL techniques to the characteristics of medical imaging tasks. The source code will be made publicly available at: https://github.com/CAMMA-public/med-moco

📄 PDF Abstract BibTeX arXiv:2402.14611

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningImage SegmentationLinear evaluationMedical Image AnalysisMedical Image SegmentationSelf-Supervised LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…
Batch Normalization 설명 없음
Focus 설명 없음
MoCo v2 MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Motivated by the findings presented in…
InfoNCE 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Understanding Dimensional Collapse in Contrastive Self-supervised Learning

2021-10-18 · ICLR 2022 4 · Li Jing, Pascal Vincent, Yann Lecun, Yuandong Tian

Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from differen…

Contrastive LearningLearning TheoryRepresentation LearningSelf-Supervised Learning

Semi-Supervised Contrastive Learning with Orthonormal Prototypes

2025-11-27 · Huanran Li, Manh Nguyen, Daniel Pimentel-Alarcón arxiv

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embed…

Contrastive LearningImage ClassificationObject Detection

Direct Coloring for Self-Supervised Enhanced Feature Decoupling

2024-12-03 · Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh

The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decoupling) as well as complete and dimensional r…

Data AugmentationRepresentation LearningSelf-Supervised Learning

Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP)

2024-03-27 · Huanran Li, Manh Nguyen, Daniel Pimentel-Alarcón

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, neural collapse, where embeddings…

Contrastive Learning

WERank: Towards Rank Degradation Prevention for Self-Supervised Learning Using Weight Regularization

2024-02-14 · Ali Saheb Pasand, Reza Moravej, Mahdi Biparva, Ali Ghodsi

A common phenomena confining the representation quality in Self-Supervised Learning (SSL) is dimensional collapse (also known as rank degeneration), where the learned representations are mapped to a low dimensional subsp…

Data AugmentationSelf-Supervised Learning