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

Showing 16511700 of 6661 papers

TitleStatusHype
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
Improving BERT Model Using Contrastive Learning for Biomedical Relation ExtractionCode1
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive LearningCode1
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory BankCode1
Self-supervised Spatial Reasoning on Multi-View Line DrawingsCode1
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled VideosCode1
Mutual Contrastive Learning for Visual Representation LearningCode1
Pri3D: Can 3D Priors Help 2D Representation Learning?Code1
Distilling Audio-Visual Knowledge by Compositional Contrastive LearningCode1
SelfReg: Self-supervised Contrastive Regularization for Domain GeneralizationCode1
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive LearningCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Contrastive Learning for Compact Single Image DehazingCode1
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Solving Inefficiency of Self-supervised Representation LearningCode1
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersCode1
Dual Contrastive Learning for Unsupervised Image-to-Image TranslationCode1
Contrastive Learning with Stronger AugmentationsCode1
Contrastive Learning for Sports Video: Unsupervised Player ClassificationCode1
Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted PoolingCode1
Bootstrapping Semantic Segmentation with Regional ContrastCode1
Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG ModelingCode1
Context-self contrastive pretraining for crop type semantic segmentationCode1
CoCoNets: Continuous Contrastive 3D Scene RepresentationsCode1
Contrastive Learning of Global-Local Video RepresentationsCode1
Localizing Visual Sounds the Hard WayCode1
Graph Contrastive ClusteringCode1
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable DirectionsCode1
Enriched Music Representations with Multiple Cross-modal Contrastive LearningCode1
Jigsaw Clustering for Unsupervised Visual Representation LearningCode1
Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain AdaptationCode1
Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity PerspectiveCode1
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive LearningCode1
Model-Contrastive Federated LearningCode1
Denoise and Contrast for Category Agnostic Shape CompletionCode1
Progressive Domain Expansion Network for Single Domain GeneralizationCode1
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationCode1
Self-supervised Graph Neural Networks without explicit negative samplingCode1
Rethinking Self-Supervised Learning: Small is BeautifulCode1
A Broad Study on the Transferability of Visual Representations with Contrastive LearningCode1
Supporting Clustering with Contrastive LearningCode1
VLGrammar: Grounded Grammar Induction of Vision and LanguageCode1
COMPLETER: Incomplete Multi-view Clustering via Contrastive PredictionCode1
Self-Supervised Classification NetworkCode1
Training GANs with Stronger Augmentations via Contrastive DiscriminatorCode1
Single Underwater Image Restoration by Contrastive LearningCode1
SPICE: Semantic Pseudo-labeling for Image ClusteringCode1
Contrastive Learning of Musical RepresentationsCode1
Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics ModelCode1
Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image SegmentationCode1
Show:102550
← PrevPage 34 of 134Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified