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 6451–6500 of 6661 papers

TitleStatusHype
Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents—0
Contrastive Learning of General-Purpose Audio RepresentationsCode0
Less can be more in contrastive learning—0
CLAR: Contrastive Learning of Auditory Representations—0
Self-supervised Co-training for Video Representation LearningCode1
What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function ApproximatorCode1
Improving Transformation Invariance in Contrastive Representation LearningCode1
MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patientsCode0
i-Mix: A Domain-Agnostic Strategy for Contrastive Representation LearningCode1
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive LearningCode0
Representation Learning via Invariant Causal MechanismsCode1
Fully Unsupervised Person Re-identification viaSelective Contrastive Learning—0
Masked Contrastive Representation Learning for Reinforcement LearningCode1
Function Contrastive Learning of Transferable Meta-Representations—0
Self-Supervised Ranking for Representation Learning—0
Viewmaker Networks: Learning Views for Unsupervised Representation LearningCode1
Contrast and Classify: Training Robust VQA ModelsCode1
An Analysis of Robustness of Non-Lipschitz NetworksCode0
MixCo: Mix-up Contrastive Learning for Visual RepresentationCode1
MS^2L: Multi-Task Self-Supervised Learning for Skeleton Based Action RecognitionCode1
MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray ModelsCode1
Contrastive Rendering for Ultrasound Image Segmentation—0
Contrastive Representation Learning: A Framework and Review—0
MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects—0
Contrastive Learning with Hard Negative SamplesCode1
Unsupervised Representation Learning by InvariancePropagationCode1
Representation Learning for Sequence Data with Deep Autoencoding Predictive ComponentsCode1
Support-set bottlenecks for video-text representation learning—0
A Contrastive Learning Approach for Training Variational Autoencoder Priors—0
CO2: Consistent Contrast for Unsupervised Visual Representation Learning—0
A Simple Framework for Uncertainty in Contrastive Learning—0
EqCo: Equivalent Rules for Self-supervised Contrastive LearningCode0
Unsupervised Reference-Free Summary Quality Evaluation via Contrastive LearningCode1
Conditional Negative Sampling for Contrastive Learning of Visual RepresentationsCode0
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Hard Negative Mixing for Contrastive LearningCode1
Joint Contrastive Learning with Infinite PossibilitiesCode1
Driver Anomaly Detection: A Dataset and Contrastive Learning ApproachCode1
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive LearningCode0
CoKe: Localized Contrastive Learning for Robust Keypoint Detection—0
Function Contrastive Learning of Transferable Representations—0
What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator—0
DROPS: Deep Retrieval of Physiological Signals via Attribute-specific Clinical Prototypes—0
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object LocalizationCode0
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
Structure Aware Negative Sampling in Knowledge Graphs—0
Label-Efficient Multi-Task Segmentation using Contrastive LearningCode1
Feature Distillation With Guided Adversarial Contrastive Learning—0
Contrastive ClusteringCode1
Show:102550
← PrevPage 130 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