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 5326–5350 of 6661 papers

TitleStatusHype
Contrastive Learning for Time Series on Dynamic Graphs—0
Boosting Star-GANs for Voice Conversion with Contrastive Discriminator—0
Federated Learning from Pre-Trained Models: A Contrastive Learning Approach—0
Statement-Level Vulnerability Detection: Learning Vulnerability Patterns Through Information Theory and Contrastive LearningCode0
Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction—0
Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation—0
S^3R: Self-supervised Spectral Regression for Hyperspectral Histopathology Image Classification—0
Mutual Harmony: Sequential Recommendation with Dual Contrastive NetworkCode0
Few-Shot Classification with Contrastive Learning—0
Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detection—0
Graph Contrastive Learning with Cross-view Reconstruction—0
Graph Contrastive Learning with Personalized Augmentation—0
SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding—0
Joint Debiased Representation and Image Clustering Learning with Self-Supervision—0
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial AttackCode0
FreeGaze: Resource-efficient Gaze Estimation via Frequency Domain Contrastive Learning—0
SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation—0
Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention PoolingCode0
Active Perception Applied To Unmanned Aerial Vehicles Through Deep Reinforcement Learning—0
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity MatchingCode0
Hyperbolic Self-supervised Contrastive Learning Based Network Anomaly Detection—0
Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural FeaturesCode0
SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive LearningCode0
MimCo: Masked Image Modeling Pre-training with Contrastive Teacher—0
Information Maximization for Extreme Pose Face Recognition—0
Show:102550
← PrevPage 214 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