paper-with-me

Papers

Probabilistic Contrastive Loss for Self-Supervised Learning

2021-12-02 · Shen Li, Jianqing Xu, Bryan Hooi

This paper proposes a probabilistic contrastive loss function for self-supervised learning. The well-known contrastive loss is deterministic and involves a temperature hyperparameter that scales the inner product between two normed feature embeddings. By reinterpreting the temperature hyperparameter as a quantity related to the radius of the hypersphere, we derive a new loss function that involves a confidence measure which quantifies uncertainty in a mathematically grounding manner. Some intriguing properties of the proposed loss function are empirically demonstrated, which agree with human-like predictions. We believe the present work brings up a new prospective to the area of contrastive learning.

📄 PDF Abstract BibTeX arXiv:2112.01642

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

2024-10-11 · Bokun Wang, Yunwen Lei, Yiming Ying, Tianbao Yang

We study the discriminative probabilistic modeling problem on a continuous domain for (multimodal) self-supervised representation learning. To address the challenge of computing the integral in the partition function for…

Representation Learning

Prototypical Contrastive Predictive Coding

2021-09-29 · ICLR 2022 4 · Kyungmin Lee

Transferring representational knowledge of a model to another is a wide-ranging topic in machine learning. Those applications include the distillation of a large supervised or self-supervised teacher model to a smaller s…

Contrastive LearningKnowledge DistillationModel CompressionSelf-Supervised Learning

Contrastive Classification and Representation Learning with Probabilistic Interpretation

2022-11-07 · Rahaf Aljundi, Yash Patel, Milan Sulc, Daniel Olmeda 외

Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recent…

ClassificationContrastive LearningRepresentation Learning

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

2023-03-23 · CVPR 2023 1 · Guofeng Mei, Hao Tang, Xiaoshui Huang, Weijie Wang 외

Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds w…

Point Cloud Registration

C$^2$VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior

2023-09-23 · Zhangkai Wu, Longbing Cao

We present a self-supervised variational autoencoder (VAE) to jointly learn disentangled and dependent hidden factors and then enhance disentangled representation learning by a self-supervised classifier to eliminate cou…

Representation Learning