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 4726–4750 of 6661 papers

TitleStatusHype
Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing—0
Multiview Contrastive Learning for Completely Blind Video Quality Assessment of User Generated ContentCode0
Unsupervised Visual Representation Learning by Synchronous Momentum Grouping—0
Self-supervised Group Meiosis Contrastive Learning for EEG-Based Emotion RecognitionCode1
Dual Contrastive Learning for Spatio-temporal Representation—0
Contrastive Deep SupervisionCode1
Contrastive Learning for Online Semi-Supervised General Continual LearningCode0
Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning—0
RUSH: Robust Contrastive Learning via Randomized Smoothing—0
A Closer Look at Invariances in Self-supervised Pre-training for 3D VisionCode0
Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's DiseaseCode0
Domain Adaptation Under Behavioral and Temporal Shifts for Natural Time Series Mobile Activity RecognitionCode0
Domain Confused Contrastive Learning for Unsupervised Domain Adaptation—0
Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio RepresentationCode1
Pixel-level Correspondence for Self-Supervised Learning from Video—0
Few-Example Clustering via Contrastive Learning—0
Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and PreparationCode1
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action RecognitionCode1
DLME: Deep Local-flatness Manifold EmbeddingCode1
Supervised Contrastive Learning Approach for Contextual Ranking—0
Learning Music-Dance Representations through Explicit-Implicit Rhythm Synchronization—0
Few-Shot Scene Classification of Optical Remote Sensing Images Leveraging Calibrated Pretext TasksCode2
Network Binarization via Contrastive LearningCode1
Unsupervised Learning for Human Sensing Using Radio Signals—0
Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrievalCode1
Show:102550
← PrevPage 190 of 267Next →
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