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 5801–5850 of 6661 papers

TitleStatusHype
Self-Supervised Representation Learning via Latent Graph Prediction—0
Self-Supervised Class-Cognizant Few-Shot ClassificationCode0
Misinformation Detection in Social Media Video Posts—0
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning—0
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkCode0
Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning—0
A Generic Self-Supervised Framework of Learning Invariant Discriminative Features—0
Adversarial Graph Contrastive Learning with Information RegularizationCode0
Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search—0
Learning long-term music representations via hierarchical contextual constraints—0
Geometric Graph Representation Learning via Maximizing Rate Reduction—0
SuperCon: Supervised Contrastive Learning for Imbalanced Skin Lesion Classification—0
From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach—0
Adults as Augmentations for Children in Facial Emotion Recognition with Contrastive Learning—0
Using Navigational Information to Learn Visual Representations—0
Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning—0
STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation—0
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion—0
Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation—0
Self-supervised Contrastive Learning for Volcanic Unrest DetectionCode0
FMP: Toward Fair Graph Message Passing against Topology Bias—0
Learning Sound Localization Better From Semantically Similar Samples—0
Self-supervised Speaker Recognition Training Using Human-Machine Dialogues—0
Low-confidence Samples Matter for Domain AdaptationCode0
Quality Assessment of Low Light Restored Images: A Subjective Study and an Unsupervised Model—0
Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation—0
The Met Dataset: Instance-level Recognition for Artworks—0
Sim2Real Object-Centric Keypoint Detection and Description—0
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition—0
Learning to Hash Naturally Sorts—0
Learning Robust Representation through Graph Adversarial Contrastive Learning—0
Generalizing similarity in noisy setups: the DIBS phenomenon—0
Contrastive Learning from Demonstrations—0
Self-Supervised Moving Vehicle Detection from Audio-Visual Cues—0
Understanding Deep Contrastive Learning via Coordinate-wise Optimization—0
Investigating Why Contrastive Learning Benefits Robustness Against Label Noise—0
Syfer: Neural Obfuscation for Private Data Release—0
Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification—0
Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud ClassificationCode0
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks—0
Pair-Level Supervised Contrastive Learning for Natural Language Inference—0
CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search—0
Modeling Multi-level Context for Informational Bias Detection by Contrastive Learning and Sentential Graph Network—0
Learning Graph Augmentations to Learn Graph RepresentationsCode0
Cross-Domain Document Layout Analysis Using Document Style Guide—0
Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning—0
Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing—0
Enhancing Hyperbolic Graph Embeddings via Contrastive Learning—0
Fair Node Representation Learning via Adaptive Data Augmentation—0
Contrastive and Selective Hidden Embeddings for Medical Image SegmentationCode0
Show:102550
← PrevPage 117 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