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 2901–2950 of 6661 papers

TitleStatusHype
Mixup Your Own PairsCode1
CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Prompting—0
A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition—0
FLIP: Cross-domain Face Anti-spoofing with Language GuidanceCode1
Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics—0
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering—0
Graph-level Representation Learning with Joint-Embedding Predictive ArchitecturesCode1
GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationCode2
Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation—0
Transferability of Representations Learned using Supervised Contrastive Learning Trained on a Multi-Domain Dataset—0
Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory—0
Investigating Deep Neural Network Architecture and Feature Extraction Designs for Sensor-based Human Activity Recognition—0
Robust Stance Detection: Understanding Public Perceptions in Social Media—0
M^33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding—0
Contrastive Continual Multi-view Clustering with Filtered Structural Fusion—0
ALEX: Towards Effective Graph Transfer Learning with Noisy Labels—0
Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive LearningCode1
Provable Training for Graph Contrastive LearningCode0
Detecting and Grounding Multi-Modal Media Manipulation and BeyondCode2
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training—0
PARTICLE: Part Discovery and Contrastive Learning for Fine-grained RecognitionCode0
Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic SegmentationCode0
Boundary-Aware Proposal Generation Method for Temporal Action Localization—0
HyperTrack: Neural Combinatorics for High Energy PhysicsCode0
Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive LearningCode1
Contrastive Speaker Embedding With Sequential Disentanglement—0
Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive LearningCode1
USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation—0
On the Sweet Spot of Contrastive Views for Knowledge-enhanced Recommendation—0
Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy—0
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You WhereCode0
A Knowledge-Driven Cross-view Contrastive Learning for EEG Representation—0
Audio Contrastive based Fine-tuning—0
DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning—0
Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems—0
A class-weighted supervised contrastive learning long-tailed bearing fault diagnosis approach using quadratic neural networkCode1
Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-trainingCode0
BitCoin: Bidirectional Tagging and Supervised Contrastive Learning based Joint Relational Triple Extraction Framework—0
BELT:Bootstrapping Electroencephalography-to-Language Decoding and Zero-Shot Sentiment Classification by Natural Language Supervision—0
TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive LearningCode1
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain GapCode0
Leveraging Negative Signals with Self-Attention for Sequential Music Recommendation—0
Semi-supervised News Discourse Profiling with Contrastive Learning—0
Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive LearningCode1
CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-ThoughtCode1
Long-tail Augmented Graph Contrastive Learning for RecommendationCode1
Visual Question Answering in the Medical Domain—0
Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-TrainingCode0
Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node TasksCode1
RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation—0
Show:102550
← PrevPage 59 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