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 6001–6050 of 6661 papers

TitleStatusHype
Interventional Video Grounding with Dual Contrastive LearningCode0
Contrastive learning for natural language-based vehicle retrievalCode0
Neighborhood Contrastive Learning for Novel Class DiscoveryCode1
Underwater Image Restoration via Contrastive Learning and a Real-world DatasetCode1
Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images—0
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples—0
Mining Better Samples for Contrastive Learning of Temporal Correspondence—0
Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis—0
Progressive Unsupervised Learning for Visual Object Tracking—0
Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency—0
Spatio-temporal Contrastive Domain Adaptation for Action Recognition—0
Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual Video Parsing—0
TS2Vec: Towards Universal Representation of Time SeriesCode1
Source-free Domain Adaptation via Avatar Prototype Generation and AdaptationCode1
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images—0
Self-supervised Video Representation Learning with Cross-Stream Prototypical ContrastingCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Novelty Detection via Contrastive Learning with Negative Data Augmentation—0
Investigating the Role of Negatives in Contrastive Representation Learning—0
A Self-supervised Method for Entity AlignmentCode1
Deep Contrastive Graph Representation via Adaptive Homotopy Learning—0
Long-Short Temporal Contrastive Learning of Video Transformers—0
Prototypical Graph Contrastive LearningCode1
Learning to Predict Visual Attributes in the Wild—0
MaCLR: Motion-aware Contrastive Learning of Representations for VideosCode0
Poisoning and Backdooring Contrastive LearningCode1
Contrastive Learning of Natural Language and Code Representations for Semantic Code Search—0
Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI ClassificationCode1
C^3: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues—0
Positional Contrastive Learning for Volumetric Medical Image SegmentationCode1
Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows—0
Bilateral Personalized Dialogue Generation with Contrastive LearningCode0
Evaluating Modules in Graph Contrastive LearningCode1
Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-IdentificationCode0
Biomedical Entity Linking with Contrastive Context MatchingCode1
Noise-robust Graph Learning by Estimating and Leveraging Pairwise InteractionsCode0
Learning Task-Relevant Representations with Selective Contrast for Reinforcement Learning in a Real-World Application—0
Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning—0
Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation—0
Hybrid Generative-Contrastive Representation LearningCode1
A comprehensive solution to retrieval-based chatbot construction—0
Towards User-Driven Neural Machine TranslationCode0
Graph Contrastive Learning AutomatedCode1
Cross-domain Contrastive Learning for Unsupervised Domain AdaptationCode0
Adversarial Graph Augmentation to Improve Graph Contrastive LearningCode1
PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive LearningCode1
Fairness-Aware Node Representation Learning—0
CLCC: Contrastive Learning for Color ConstancyCode1
Pretrained Encoders are All You NeedCode1
Neighborhood Contrastive Learning Applied to Online Patient MonitoringCode1
Show:102550
← PrevPage 121 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