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 2076–2100 of 6661 papers

TitleStatusHype
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning—0
RAR: Retrieving And Ranking Augmented MLLMs for Visual RecognitionCode2
USE: Dynamic User Modeling with Stateful Sequence ModelsCode0
Towards Principled Representation Learning from Videos for Reinforcement LearningCode1
Do Generated Data Always Help Contrastive Learning?Code1
Non-negative Contrastive LearningCode1
UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All—0
Automated Contrastive Learning Strategy Search for Time Series—0
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature RepresentationCode0
CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite—0
Time Series Compression using Quaternion Valued Neural Networks and Quaternion Backpropagation—0
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised LearningCode1
End-to-end multi-modal product matching in fashion e-commerce—0
Open-World Semi-Supervised Learning for Node ClassificationCode1
Investigating the Benefits of Projection Head for Representation Learning—0
Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential RecommendationCode1
Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain AdaptationCode0
RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive LearningCode0
Improving the Robustness of Dense Retrievers Against Typos via Multi-Positive Contrastive LearningCode0
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling CasesCode1
Probabilistic World Modeling with Asymmetric Distance Measure—0
Game and Reference: Policy Combination Synthesis for Epidemic Prevention and Control—0
Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings—0
MeDSLIP: Medical Dual-Stream Language-Image Pre-training for Fine-grained AlignmentCode0
Improving Medical Multi-modal Contrastive Learning with Expert AnnotationsCode0
Show:102550
← PrevPage 84 of 267Next →
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