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 4351–4400 of 6661 papers

TitleStatusHype
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive AdaptationCode0
Supervised Contrastive Learning with Tree-Structured Parzen Estimator Bayesian Optimization for Imbalanced Tabular Data—0
HAVANA: Hard negAtiVe sAmples aware self-supervised coNtrastive leArning for Airborne laser scanning point clouds semantic segmentation—0
DyTed: Disentangled Representation Learning for Discrete-time Dynamic GraphCode1
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood LearningCode0
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell CheckingCode1
Sentiment-Aware Word and Sentence Level Pre-training for Sentiment AnalysisCode1
MedCLIP: Contrastive Learning from Unpaired Medical Images and TextCode2
Universal hidden monotonic trend estimation with contrastive learning—0
Unsupervised visualization of image datasets using contrastive learningCode1
Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation—0
AdaGCL: Adaptive Subgraph Contrastive Learning to Generalize Large-scale Graph TrainingCode0
Unifying Graph Contrastive Learning with Flexible Contextual ScopesCode1
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive LearningCode1
HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold—0
Correlation between Alignment-Uniformity and Performance of Dense Contrastive RepresentationsCode0
Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog—0
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent DiscoveryCode0
Weakly Supervised Face Naming with Symmetry-Enhanced Contrastive LossCode0
Improving Contrastive Learning on Visually Homogeneous Mars Rover Images—0
Supervised Prototypical Contrastive Learning for Emotion Recognition in ConversationCode1
Non-Contrastive Learning Meets Language-Image Pre-TrainingCode0
Indoor Smartphone SLAM with Learned Echoic Location Features—0
Towards Effective Image Manipulation Detection with Proposal Contrastive LearningCode1
Attention-Based Audio Embeddings for Query-by-ExampleCode0
Adaptive Contrastive Learning with Dynamic Correlation for Multi-Phase Organ SegmentationCode0
Semantic Segmentation with Active Semi-Supervised Representation Learning—0
How Mask Matters: Towards Theoretical Understandings of Masked AutoencodersCode1
Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative RepresentationsCode3
Improving Radiology Summarization with Radiograph and Anatomy Prompts—0
Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-IdentificationCode1
Instance Segmentation with Cross-Modal Consistency—0
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge RepresentationCode1
Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning—0
Blind Super-Resolution for Remote Sensing Images via Conditional Stochastic Normalizing Flows—0
Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive LearningCode1
Invariance-adapted decomposition and Lasso-type contrastive learning—0
TractoSCR: A Novel Supervised Contrastive Regression Framework for Prediction of Neurocognitive Measures Using Multi-Site Harmonized Diffusion MRI Tractography—0
LEAVES: Learning Views for Time-Series Data in Contrastive Learning—0
Low-resource Neural Machine Translation with Cross-modal AlignmentCode1
Closed-book Question Generation via Contrastive LearningCode0
RaP: Redundancy-aware Video-language Pre-training for Text-Video RetrievalCode0
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLCode1
Language Agnostic Multilingual Information Retrieval with Contrastive LearningCode0
Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and WhistlesCode0
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object TrackingCode2
Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation LearningCode1
Self-supervised video pretraining yields robust and more human-aligned visual representations—0
Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive LearningCode2
Self-Attention Message Passing for Contrastive Few-Shot LearningCode1
Show:102550
← PrevPage 88 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