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 3301–3350 of 6661 papers

TitleStatusHype
Description-Enhanced Label Embedding Contrastive Learning for Text ClassificationCode0
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Generate to Understand for RepresentationCode1
Learning on Graphs under Label Noise—0
Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrieval—0
Contrastive Learning-Based Audio to Lyrics Alignment for Multiple LanguagesCode1
GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition—0
Enhanced Multimodal Representation Learning with Cross-modal KD—0
Time-aware Graph Structure Learning via Sequence Prediction on Temporal GraphsCode1
CARL-G: Clustering-Accelerated Representation Learning on Graphs—0
A Pairing Enhancement Approach for Aspect Sentiment Triplet Extraction—0
Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework—0
Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient EncoderCode0
Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression ValuesCode0
Liquidity takers behavior representation through a contrastive learning approach—0
DocumentCLIP: Linking Figures and Main Body Text in Reflowed DocumentsCode1
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point CloudCode0
Factorized Contrastive Learning: Going Beyond Multi-view RedundancyCode1
A brief review of contrastive learning applied to astrophysics—0
R-MAE: Regions Meet Masked AutoencodersCode1
Contrastive Representation Disentanglement for Clustering—0
Regularizing with Pseudo-Negatives for Continual Self-Supervised LearningCode0
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification—0
Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce—0
Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image—0
Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation—0
Automatic retrieval of corresponding US views in longitudinal examinationsCode0
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement—0
Randomized 3D Scene Generation for Generalizable Self-Supervised Pre-Training—0
ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function—0
Rethinking Weak Supervision in Helping Contrastive Learning—0
Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive LearningCode0
On the Generalization of Multi-modal Contrastive LearningCode1
Randomized Schur Complement Views for Graph Contrastive LearningCode0
Unraveling Projection Heads in Contrastive Learning: Insights from Expansion and Shrinkage—0
BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and GraphsCode1
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline DataCode1
Identifying Shared Decodable Concepts in the Human Brain Using Image-Language Foundation Models—0
YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp DetectionCode0
Click: Controllable Text Generation with Sequence Likelihood Contrastive LearningCode1
Subgraph Networks Based Contrastive Learning—0
ReContrast: Domain-Specific Anomaly Detection via Contrastive ReconstructionCode1
Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-TrainingCode1
LRVS-Fashion: Extending Visual Search with Referring InstructionsCode1
Asymmetric Patch Sampling for Contrastive LearningCode1
SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives—0
LibAUC: A Deep Learning Library for X-Risk OptimizationCode2
rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological MeasurementCode1
MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning—0
ContraBAR: Contrastive Bayes-Adaptive Deep RLCode1
Show:102550
← PrevPage 67 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