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 5876–5900 of 6661 papers

TitleStatusHype
Feature Extraction Framework based on Contrastive Learning with Adaptive Positive and Negative Samples—0
Bootstrapping Informative Graph Augmentation via A Meta Learning ApproachCode0
Supervised Contrastive Learning for Recommendation—0
Cross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrapping—0
On the Effectiveness of Sampled Softmax Loss for Item Recommendation—0
Semi-Supervised Clustering with Contrastive Learning for Discovering New Intents—0
Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning—0
Self-supervised Learning from 100 Million Medical Images—0
Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization—0
Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings—0
Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning—0
EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval—0
Knowledge-Driven Self-Supervised Representation Learning for Facial Action Unit Recognition—0
Contextual Outpainting With Object-Level Contrastive Learning—0
Learning Video Representations of Human Motion From Synthetic Data—0
Contrastive Learning for Space-Time Correspondence via Self-Cycle Consistency—0
UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection—0
Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations—0
A Hybrid Egocentric Activity Anticipation Framework via Memory-Augmented Recurrent and One-Shot Representation Forecasting—0
Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification—0
Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning—0
Id-Free Person Similarity Learning—0
Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization—0
Align Representations With Base: A New Approach to Self-Supervised Learning—0
One-Bit Active Query With Contrastive Pairs—0
Show:102550
← PrevPage 236 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