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 5101–5125 of 6661 papers

TitleStatusHype
How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?—0
Robust Mean Teacher for Continual and Gradual Test-Time Adaptation—0
Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction—0
Supervised Contrastive Learning on Blended Images for Long-tailed Recognition—0
TCBERT: A Technical Report for Chinese Topic Classification BERT—0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier—0
Unifying Vision-Language Representation Space with Single-tower Transformer—0
CLAWSAT: Towards Both Robust and Accurate Code ModelsCode0
Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning—0
Cross-Modal Contrastive Learning for Robust Reasoning in VQACode0
Auto-Focus Contrastive Learning for Image Manipulation Detection—0
Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic GraphCode0
Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective—0
When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method—0
Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure—0
Contrastive Knowledge Graph Error DetectionCode0
The Runner-up Solution for YouTube-VIS Long Video Challenge 2022—0
Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information—0
FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data—0
ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer EvaluationCode0
Self-Supervised Visual Representation Learning via Residual Momentum—0
Anomaly Detection via Multi-Scale Contrasted Memory—0
Learning Reward Functions for Robotic Manipulation by Observing Humans—0
Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite ImageryCode0
An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022—0
Show:102550
← PrevPage 205 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