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 5151–5175 of 6661 papers

TitleStatusHype
How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning—0
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval—0
How to Bridge Spatial and Temporal Heterogeneity in Link Prediction? A Contrastive Method—0
How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?—0
How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?—0
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval—0
SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking—0
Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration—0
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training—0
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models—0
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations—0
Hybrid Augmented Automated Graph Contrastive Learning—0
Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking—0
Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis—0
Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification—0
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners—0
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id—0
Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning—0
HyCIR: Boosting Zero-Shot Composed Image Retrieval with Synthetic Labels—0
Hyperbolic Contrastive Learning—0
Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding—0
Hyperbolic Face Anti-Spoofing—0
Hyperbolic Hierarchical Contrastive Hashing—0
Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classification—0
Hyperbolic Knowledge Transfer in Cross-Domain Recommendation System—0
Show:102550
← PrevPage 207 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