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 5401–5425 of 6661 papers

TitleStatusHype
Fuse and Attend: Generalized Embedding Learning for Art and Sketches—0
GraphTTA: Test Time Adaptation on Graph Neural Networks—0
Disentangled Contrastive Learning for Social RecommendationCode0
Siamese Prototypical Contrastive Learning—0
SelF-Eval: Self-supervised Fine-grained Dialogue EvaluationCode0
Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation—0
CommitBART: A Large Pre-trained Model for GitHub Commits—0
CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation—0
DICE: Data-Efficient Clinical Event Extraction with Generative Models—0
ARIEL: Adversarial Graph Contrastive LearningCode0
C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification—0
Contrastive Learning for Joint Normal Estimation and Point Cloud FilteringCode0
A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection—0
Enhancing Graph Contrastive Learning with Node Similarity—0
Contrastive Learning for OOD in Object detectionCode0
Motion Sensitive Contrastive Learning for Self-supervised Video Representation—0
Contrastive Learning for Object DetectionCode0
Path-aware Siamese Graph Neural Network for Link PredictionCode0
Self-supervised Multi-modal Training from Uncurated Image and Reports Enables Zero-shot Oversight Artificial Intelligence in RadiologyCode0
Multi-View Pre-Trained Model for Code Vulnerability Identification—0
Improving COVID-19 CT Classification of CNNs by Learning Parameter-Efficient Representation—0
Improving Micro-video Recommendation by Controlling Position Bias—0
Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentation—0
Understanding Masked Image Modeling via Learning Occlusion Invariant Feature—0
AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learning—0
Show:102550
← PrevPage 217 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