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 776–800 of 6661 papers

TitleStatusHype
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual RepresentationsCode3
WildSAT: Learning Satellite Image Representations from Wildlife Observations—0
Multimodal Hypothetical Summary for Retrieval-based Multi-image Question AnsweringCode0
DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation—0
Balanced Gradient Sample Retrieval for Enhanced Knowledge Retention in Proxy-based Continual Learning—0
CLDG: Contrastive Learning on Dynamic GraphsCode1
ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting—0
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive LearningCode0
What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood ContextCode0
Multi-view Granular-ball Contrastive Clustering—0
Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language ModelsCode1
I0T: Embedding Standardization Method Towards Zero Modality GapCode1
MixRec: Heterogeneous Graph Collaborative FilteringCode1
Cluster-guided Contrastive Class-imbalanced Graph Classification—0
ClarityEthic: Explainable Moral Judgment Utilizing Contrastive Ethical Insights from Large Language Models—0
CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information RetrievalCode1
Multi-Domain Features Guided Supervised Contrastive Learning for Radar Target Detection—0
Detecting Emotional Incongruity of Sarcasm by Commonsense Reasoning—0
DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image SegmentationCode1
Multi-head attention debiasing and contrastive learning for mitigating Dataset Artifacts in Natural Language Inference—0
Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced RegressionCode0
Personalized LLM for Generating Customized Responses to the Same Query from Different UsersCode0
Generalization Analysis for Deep Contrastive Representation Learning—0
Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models—0
Show:102550
← PrevPage 32 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