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
Optimizing Test-Time Query Representations for Dense RetrievalCode1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
Self-Supervised Time Series Representation Learning via Cross Reconstruction TransformerCode1
RankGen: Improving Text Generation with Large Ranking ModelsCode1
Domain Enhanced Arbitrary Image Style Transfer via Contrastive LearningCode1
A graph-transformer for whole slide image classificationCode1
A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation ExtractionCode1
Masked Image Modeling with Denoising ContrastCode1
Free Lunch for Surgical Video Understanding by Distilling Self-SupervisionsCode1
FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive SummarizationCode1
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and IsotropizationCode1
Near out-of-distribution detection for low-resolution radar micro-Doppler signaturesCode1
Multiplexed Immunofluorescence Brain Image Analysis Using Self-Supervised Dual-Loss Adaptive Masked AutoencoderCode1
Learning Non-target Knowledge for Few-shot Semantic SegmentationCode1
EASE: Entity-Aware Contrastive Learning of Sentence EmbeddingCode1
Cross-modal Contrastive Learning for Speech TranslationCode1
A Simple Contrastive Learning Objective for Alleviating Neural Text DegenerationCode1
UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive LearningCode1
HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation ExtractionCode1
Contrastive Learning for Prompt-Based Few-Shot Language LearnersCode1
Knowledge Graph Contrastive Learning for RecommendationCode1
Contrastive Learning for Improving ASR Robustness in Spoken Language UnderstandingCode1
Debiased Contrastive Learning of Unsupervised Sentence RepresentationsCode1
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance DetectionCode1
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense InferenceCode1
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little CostCode1
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive LearningCode1
SCS-Co: Self-Consistent Style Contrastive Learning for Image HarmonizationCode1
RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive LearningCode1
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype ContrastCode1
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning FrameworkCode1
A Review-aware Graph Contrastive Learning Framework for RecommendationCode1
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio RepresentationCode1
Hypergraph Contrastive Collaborative FilteringCode1
Self-Supervised Contrastive Learning for Singing VoicesCode1
Contrastive Learning for Knowledge TracingCode1
MCSE: Multimodal Contrastive Learning of Sentence EmbeddingsCode1
Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span PredictionCode1
SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-IdentificationCode1
Contrastive Test-Time AdaptationCode1
On Distribution Shift in Learning-based Bug DetectorsCode1
PreTraM: Self-Supervised Pre-training via Connecting Trajectory and MapCode1
Video Moment Retrieval from Text Queries via Single Frame AnnotationCode1
Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender SystemCode1
Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled DataCode1
Attributed Graph Clustering with Dual Redundancy ReductionCode1
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive LearningCode1
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment AnalysisCode1
Contrastive Learning with Hard Negative Entities for Entity Set ExpansionCode1
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive LearningCode1
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