SOTAVerified

Contrastive Learning

Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.

It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.

(Image credit: Schroff et al. 2015)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3901–3950 of 6661 papers

TitleStatusHype
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset SelectionCode0
Multi-view Feature Extraction based on Dual Contrastive Head—0
Continuous Learning for Android Malware DetectionCode1
Diagnosing and Rectifying Vision Models using LanguageCode1
SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation—0
Disentangled Causal Embedding With Contrastive Learning For Recommender SystemCode1
Cluster-Level Contrastive Learning for Emotion Recognition in ConversationsCode1
Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining ApproachCode1
APAM: Adaptive Pre-training and Adaptive Meta Learning in Language Model for Noisy Labels and Long-tailed Learning—0
Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking—0
Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning—0
Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous InputsCode1
Spectral Augmentations for Graph Contrastive Learning—0
Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection—0
Adversarial Learning Data Augmentation for Graph Contrastive Learning in RecommendationCode0
Rethinking Robust Contrastive Learning from the Adversarial PerspectiveCode0
Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalization—0
CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning—0
Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action RecognitionCode0
Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition—0
Contrastive Collaborative Filtering for Cold-Start Item RecommendationCode1
Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image CaptioningCode0
MOMA:Distill from Self-Supervised Teachers—0
Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction PerspectiveCode1
Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints—0
Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning—0
Bridging the Emotional Semantic Gap via Multimodal Relevance Estimation—0
Contrastive Learning with Consistent RepresentationsCode0
Hyperbolic Contrastive Learning—0
Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases—0
A Deep Behavior Path Matching Network for Click-Through Rate Prediction—0
A latent space for unsupervised MR image quality control via artifact assessmentCode1
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural NetworksCode1
Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive LearningCode0
NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese NetworksCode0
ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product SearchCode1
NoiseTransfer: Image Noise Generation with Contrastive EmbeddingsCode0
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain AdaptationCode0
GaitSADA: Self-Aligned Domain Adaptation for mmWave Gait RecognitionCode1
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World AttacksCode1
Direct Preference-based Policy Optimization without Reward ModelingCode1
Massively Scaling Heteroscedastic Classifiers—0
The Influences of Color and Shape Features in Visual Contrastive Learning—0
SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking—0
Mutual Wasserstein Discrepancy Minimization for Sequential RecommendationCode1
Unbiased and Efficient Self-Supervised Incremental Contrastive LearningCode0
Bayesian Self-Supervised Contrastive LearningCode0
Leveraging the Third Dimension in Contrastive Learning—0
Understanding Self-Supervised Pretraining with Part-Aware Representation LearningCode0
Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks—0
Show:102550
← PrevPage 79 of 134Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified