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 551575 of 6661 papers

TitleStatusHype
Learning to Embed Time Series Patches IndependentlyCode1
Soft Contrastive Learning for Time SeriesCode1
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving SystemsCode1
A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide GenerationCode1
TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation LearningCode1
Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent RecognitionCode1
Energy-based learning algorithms for analog computing: a comparative studyCode1
Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQACode1
DVIS++: Improved Decoupled Framework for Universal Video SegmentationCode1
Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context ModelingCode1
Object-Aware Domain Generalization for Object DetectionCode1
Knowledge Graph Error Detection with Contrastive Confidence AdaptionCode1
ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide SequencingCode1
Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor DetectorCode1
Generalized Category Discovery with Large Language Models in the LoopCode1
SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on TwitterCode1
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal PerspectiveCode1
CETN: Contrast-enhanced Through Network for CTR PredictionCode1
Multi-Modality is All You Need for Transferable Recommender SystemsCode1
Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound ClassificationCode1
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed DataCode1
Patch-wise Graph Contrastive Learning for Image TranslationCode1
Toward Real Text Manipulation Detection: New Dataset and New SolutionCode1
Transformer-based No-Reference Image Quality Assessment via Supervised Contrastive LearningCode1
Hallucination Augmented Contrastive Learning for Multimodal Large Language ModelCode1
Show:102550
← PrevPage 23 of 267Next →

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