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

February 8, 2023

Multi-view Feature Extraction based on Dual Contrastive Head
Hongjie Zhang
Contrastive Learning Contrastive Loss Dual System Contrastive Head

February 7, 2023

February 6, 2023

February 5, 2023

February 4, 2023

MOMA:Distill from Self-Supervised Teachers
Yuchong Yao, Nandakishor Desai, Marimuthu Palaniswami
Contrastive Learning Self Supervised Representation Learning Masked AutoEncoder Semi Supervised Teacher Student Masked Image

February 3, 2023

February 2, 2023

Hyperbolic Contrastive Learning
Yun Yue, Fangzhou Lin, Kazunori D Yamada, Ziming Zhang
Contrastive Learning Latent Geometry

February 1, 2023

Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases
T. Y. S. S Santosh, Marcel Perez San Blas, Phillip Kemper, Matthias Grabmair
Contrastive Learning Classification Code Contrastive Loss Case Relevance Human Right News Classification Task Dependency Multi Label Contrastive

Contrastive Learning

Papers

Multi-view Feature Extraction based on Dual Contrastive Head

Cluster-Level Contrastive Learning for Emotion Recognition in Conversations

Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach

APAM: Adaptive Pre-training and Adaptive Meta Learning in Language Model for Noisy Labels and Long-tailed Learning

Spectral Augmentations for Graph Contrastive Learning

Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning

Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking

Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection

Rethinking Robust Contrastive Learning from the Adversarial Perspective

CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning

Adversarial Learning Data Augmentation for Graph Contrastive Learning in Recommendation

Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition

MOMA:Distill from Self-Supervised Teachers

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective

SCCAM: Supervised Contrastive Convolutional Attention Mechanism for Ante-hoc Interpretable Fault Diagnosis with Limited Fault Samples

Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints

Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning

Contrastive Learning with Consistent Representations

Hyperbolic Contrastive Learning

Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases