Contrastive Loss Function

Contrastive loss functions are a powerful technique in machine learning that learns representations by maximizing the similarity between similar data points (e.g., augmented views of an image) while minimizing similarity between dissimilar ones. Current research focuses on improving robustness to noise, adapting contrastive learning to various architectures (including transformers and prototypical networks), and integrating it with other techniques like Bayesian learning and clustering for tasks such as class-incremental learning, recommendation systems, and unsupervised person re-identification. These advancements are significantly impacting fields like computer vision, natural language processing, and bioinformatics by enabling effective learning from unlabeled or weakly labeled data, leading to improved model performance and efficiency.

Papers

October 17, 2024

Similarity-Dissimilarity Loss with Supervised Contrastive Learning for Multi-label Classification
Guangming Huang, Yunfei Long, Cunjin Luo, Sheng Liu
Contrastive Learning Multi Label Multi Label Classification Supervised Contrastive Learning Contrastive Loss Function Similarity Loss

June 12, 2024

To be Continuous, or to be Discrete, Those are Bits of Questions
Yiran Wang, Masao Utiyama
Yes No Question Discrete Representation Data Representation P Bit Contrastive Loss Function Contrastive Hashing

May 17, 2024

Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning
Nisha L. Raichur, Lucas Heublein, Tobias Feigl, Alexander Rügamer, Christopher Mutschler, Felix Ott
Continual LEArning Contrastive Loss Latent Representation Class Incremental Learning Prototypical Contrastive Learning Contrastive Loss Function

February 18, 2024

Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering
Peijie Sun, Le Wu, Kun Zhang, Xiangzhi Chen, Meng Wang
Contrastive Learning Loss Function Contrastive Loss Collaborative Filtering Supervised Contrastive Learning Contrastive Loss Function

January 2, 2024

Boosting Transformer's Robustness and Efficacy in PPG Signal Artifact Detection with Self-Supervised Learning
Thanh-Dung Le
Contrastive Learning Native Robustness Self Supervised Learning PPG Signal Contrastive Loss Function

September 20, 2023

CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought
Bowen Zhang, Kehua Chang, Chunping Li
Contrastive Learning Sentence Embeddings Contrastive Loss Function Unsupervised Sentence Representation Noise BERT

September 6, 2023

Contrastive Learning as Kernel Approximation
Konstantinos Christopher Tsiolis
Contrastive Learning Loss Function Kernel Approximation Contrastive Loss Function

July 14, 2023

Training Discrete Energy-Based Models with Energy Discrepancy
Tobias Schröder, Zijing Ou, Yingzhen Li, Andrew B. Duncan
Full Model Energy Based Model Image Datasets Contrastive Loss Function Energy Discrepancy

May 18, 2023

Tuned Contrastive Learning
Chaitanya Animesh, Manmohan Chandraker
Contrastive Learning Loss Function Self Supervised Visual Representation Contrastive Loss Function

May 4, 2023

Contrastive losses as generalized models of global epistasis
David H. Brookes, Jakub Otwinowski, Sam Sinai
Full Model Fitness Function Contrastive Loss Function

July 1, 2022

Studying the impact of magnitude pruning on contrastive learning methods
Francesco Corti, Rahim Entezari, Sara Hooker, Davide Bacciu, Olga Saukh
Contrastive Learning Global Impact Cross Entropy Loss Earthquake Magnitude Contrastive Loss Function Representation Quality

April 28, 2022

Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval
Maurits Bleeker, Andrew Yates, Maarten de Rijke
Contrastive Loss Contrastive Loss Function Feature Suppression Image Caption Retrieval

March 21, 2022

Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
Jiawei Zhang, Xiang Wang, Xiao Bai, Chen Wang, Lei Huang, Yimin Chen, Lin Gu, Jun Zhou, Tatsuya Harada, Edwin R. Hancock
Contrastive Loss Function Stereo Network Stereo Matching Network Feature Consistency

January 28, 2022

Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification
He Sun, Mingkun Li, Chun-Guang Li
Contrastive Loss Person Re Identification Contrastive Loss Function Ensemble Clustering

January 12, 2022

Robust Contrastive Learning against Noisy Views
Ching-Yao Chuang, R Devon Hjelm, Xin Wang, Vibhav Vineet, Neel Joshi, Antonio Torralba, Stefanie Jegelka, Yale Song
Contrastive Learning Synthesized View Contrastive Loss Function Symmetric Loss Robust Contrastive Learning

Contrastive Loss Function

Papers

Similarity-Dissimilarity Loss with Supervised Contrastive Learning for Multi-label Classification

To be Continuous, or to be Discrete, Those are Bits of Questions

Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning

Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering

Boosting Transformer's Robustness and Efficacy in PPG Signal Artifact Detection with Self-Supervised Learning

CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought

Contrastive Learning as Kernel Approximation

Training Discrete Energy-Based Models with Energy Discrepancy

Tuned Contrastive Learning

Contrastive losses as generalized models of global epistasis

Studying the impact of magnitude pruning on contrastive learning methods

Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval

Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective

Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification

Robust Contrastive Learning against Noisy Views