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 1251–1300 of 6661 papers

TitleStatusHype
Biomedical Entity Linking with Contrastive Context MatchingCode1
DeepCRF: Deep Learning-Enhanced CSI-Based RF Fingerprinting for Channel-Resilient WiFi Device IdentificationCode1
Large Scale Adversarial Representation LearningCode1
Contrastive Learning of Sentence Embeddings from ScratchCode1
BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityCode1
Deep Multiview Clustering by Contrasting Cluster AssignmentsCode1
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at ScaleCode1
Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learningCode1
Hierarchically Self-Supervised Transformer for Human Skeleton Representation LearningCode1
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable DirectionsCode1
Anatomical Foundation Models for Brain MRIsCode1
Deep Multi-View Subspace Clustering with Anchor GraphCode1
Hierarchical Verbalizer for Few-Shot Hierarchical Text ClassificationCode1
Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven OptimizationCode1
Degradation-Aware Self-Attention Based Transformer for Blind Image Super-ResolutionCode1
Contrastive Learning for Cold-Start RecommendationCode1
Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object DetectionCode1
Contrastive Learning for Compact Single Image DehazingCode1
Black-Box Attack against GAN-Generated Image Detector with Contrastive PerturbationCode1
ConDA: Contrastive Domain Adaptation for AI-generated Text DetectionCode1
Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive LearningCode1
Contrastive Learning for Cross-Domain Open World RecognitionCode1
Contrastive Learning of Musical RepresentationsCode1
Denoise and Contrast for Category Agnostic Shape CompletionCode1
DenoSent: A Denoising Objective for Self-Supervised Sentence Representation LearningCode1
Denoising Diffusion Autoencoders are Unified Self-supervised LearnersCode1
Blind Localization and Clustering of Anomalies in TexturesCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Alleviating Exposure Bias via Contrastive Learning for Abstractive Text SummarizationCode1
HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model PretrainingCode1
Hierarchical Consensus Network for Multiview Feature LearningCode1
Diffusion-based Contrastive Learning for Sequential RecommendationCode1
Contrastive Learning for Improving ASR Robustness in Spoken Language UnderstandingCode1
Learning from History: Task-agnostic Model Contrastive Learning for Image RestorationCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell CheckingCode1
Contrastive Learning for Knowledge TracingCode1
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive LearningCode1
Boosting Contrastive Self-Supervised Learning with False Negative CancellationCode1
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery CluesCode1
Automated Essay Scoring via Pairwise Contrastive RegressionCode1
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label ClassificationCode1
Boosting Few-Shot Classification with View-Learnable Contrastive LearningCode1
HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation ExtractionCode1
ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology ImagesCode1
Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Direct Preference-based Policy Optimization without Reward ModelingCode1
Contrastive Learning for Neural Topic ModelCode1
Contrastive Learning of User Behavior Sequence for Context-Aware Document RankingCode1
Show:102550
← PrevPage 26 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