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 6551–6600 of 6661 papers

TitleStatusHype
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-TrainingCode1
Vehicle Trajectory Prediction by Transfer Learning of Semi-Supervised Models—0
Representation Learning via Adversarially-Contrastive Optimal Transport—0
Contrastive Code Representation LearningCode1
InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive LearningCode1
Contrastive Multiple Correspondence Analysis (cMCA): Using Contrastive Learning to Identify Latent Subgroups in Political PartiesCode0
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge DistillationCode1
Data Augmenting Contrastive Learning of Speech Representations in the Time DomainCode1
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalCode1
Debiased Contrastive LearningCode1
Subject-Aware Contrastive Learning for BiosignalsCode1
SCE: Scalable Network Embedding from Sparsest CutCode0
Video Representation Learning with Visual Tempo ConsistencyCode1
Unsupervised Deep Representation Learning and Few-Shot Classification of PolSAR Images—0
On Equivariant and Invariant Learning of Object Landmark RepresentationsCode1
Domain Contrast for Domain Adaptive Object Detection—0
Disentangle Perceptual Learning through Online Contrastive Learning—0
ContraGAN: Contrastive Learning for Conditional Image Generation—0
Unsupervised Image Classification for Deep Representation LearningCode0
Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual RepresentationsCode1
Joint Contrastive Learning for Unsupervised Domain AdaptationCode1
Contrastive learning of global and local features for medical image segmentation with limited annotationsCode1
GCC: Graph Contrastive Coding for Graph Neural Network Pre-TrainingCode1
Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsCode2
Contrastive Learning for Weakly Supervised Phrase GroundingCode1
Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images—0
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate ReductionCode1
Improved Conditional Flow Models for Molecule to Image SynthesisCode0
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels—0
Adversarial Self-Supervised Contrastive LearningCode1
Knowledge Distillation Meets Self-SupervisionCode1
Pairwise Supervision Can Provably Elicit a Decision Boundary—0
Quasi-Dense Similarity Learning for Multiple Object TrackingCode1
DisCont: Self-Supervised Visual Attribute Disentanglement using Context VectorsCode1
Multi-view Contrastive Learning for Online Knowledge DistillationCode1
Deep Graph Contrastive Representation LearningCode1
DeCLUTR: Deep Contrastive Learning for Unsupervised Textual RepresentationsCode1
Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning—0
CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning—0
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDCode1
CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and PatientsCode1
On Mutual Information in Contrastive Learning for Visual Representations—0
Network Comparison with Interpretable Contrastive Network Representation LearningCode1
Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems—0
What Makes for Good Views for Contrastive Learning?—0
Understanding Contrastive Representation Learning through Alignment and Uniformity on the HypersphereCode1
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural LanguageCode1
On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors—0
Prototypical Contrastive Learning of Unsupervised RepresentationsCode1
Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring ExpressionsCode1
Show:102550
← PrevPage 132 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