Contrastive Learning
Contrastive learning is a self-supervised machine learning technique that aims to learn robust data representations by contrasting similar and dissimilar data points. Current research focuses on applying contrastive learning to diverse modalities, including images, audio, text, and time-series data, often within multimodal frameworks and using architectures like MoCo and SimCLR, and exploring its application in various tasks such as object detection, speaker verification, and image dehazing. This approach is significant because it allows for effective learning from unlabeled or weakly labeled data, improving model generalization and performance across numerous applications, particularly in scenarios with limited annotated data or significant domain shifts.
Papers
Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
Jihai Zhang, Xiang Lan, Xiaoye Qu, Yu Cheng, Mengling Feng, Bryan Hooi
Substrate Scope Contrastive Learning: Repurposing Human Bias to Learn Atomic Representations
Wenhao Gao, Priyanka Raghavan, Ron Shprints, Connor W. Coley
PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
Junjian Lu, Siwei Liu, Dmitrii Kobylianski, Etienne Dreyer, Eilam Gross, Shangsong Liang
Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering
Peijie Sun, Le Wu, Kun Zhang, Xiangzhi Chen, Meng Wang
Fusion of Diffusion Weighted MRI and Clinical Data for Predicting Functional Outcome after Acute Ischemic Stroke with Deep Contrastive Learning
Chia-Ling Tsai, Hui-Yun Su, Shen-Feng Sung, Wei-Yang Lin, Ying-Ying Su, Tzu-Hsien Yang, Man-Lin Mai
Training Class-Imbalanced Diffusion Model Via Overlap Optimization
Divin Yan, Lu Qi, Vincent Tao Hu, Ming-Hsuan Yang, Meng Tang
Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation
Xinjian Zhao, Liang Zhang, Yang Liu, Ruocheng Guo, Xiangyu Zhao
Parametric Augmentation for Time Series Contrastive Learning
Xu Zheng, Tianchun Wang, Wei Cheng, Aitian Ma, Haifeng Chen, Mo Sha, Dongsheng Luo
$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
Yiwei Lu, Guojun Zhang, Sun Sun, Hongyu Guo, Yaoliang Yu
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter
Sequential Recommendation on Temporal Proximities with Contrastive Learning and Self-Attention
Hansol Jung, Hyunwoo Seo, Chiehyeon Lim
Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
Yinglun Xu, Rohan Gumaste, Gagandeep Singh
FESS Loss: Feature-Enhanced Spatial Segmentation Loss for Optimizing Medical Image Analysis
Charulkumar Chodvadiya, Navyansh Mahla, Kinshuk Gaurav Singh, Kshitij Sharad Jadhav
Modeling Balanced Explicit and Implicit Relations with Contrastive Learning for Knowledge Concept Recommendation in MOOCs
Hengnian Gu, Zhiyi Duan, Pan Xie, Dongdai Zhou
Contrastive Learning for Regression on Hyperspectral Data
Mohamad Dhaini, Maxime Berar, Paul Honeine, Antonin Van Exem
Injecting Wiktionary to improve token-level contextual representations using contrastive learning
Anna Mosolova, Marie Candito, Carlos Ramisch
Contrastive Multiple Instance Learning for Weakly Supervised Person ReID
Jacob Tyo, Zachary C. Lipton
Topic Modeling as Multi-Objective Contrastive Optimization
Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu