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 2726–2750 of 6661 papers

TitleStatusHype
Bridging Text and Image for Artist Style Transfer via Contrastive Learning—0
Anomalies, Representations, and Self-Supervision—0
Contrastive Learning with Counterfactual Explanations for Radiology Report Generation—0
Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries—0
Annotation-Efficient Untrimmed Video Action Recognition—0
LiPost: Improved Content Understanding With Effective Use of Multi-task Contrastive Learning—0
Contrastive Learning With Audio Discrimination For Customizable Keyword Spotting In Continuous Speech—0
Contrastive Learning with Adversarial Examples—0
Annotated Guidelines and Building Reference Corpus for Myanmar-English Word Alignment—0
Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning—0
Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencoder—0
Contrastive Learning Via Equivariant Representation—0
Contrastive Learning Using Spectral Methods—0
Bridging Contrastive Learning and Domain Adaptation: Theoretical Perspective and Practical Application—0
Graph Contrastive Learning under Heterophily via Graph Filters—0
An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding—0
Contrastive Learning to Improve Retrieval for Real-world Fact Checking—0
Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex—0
Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification—0
Contrastive Learning Through Time—0
Contrastive Learning Subspace for Text Clustering—0
Bridge the Gap between Language models and Tabular Understanding—0
ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification—0
A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation—0
Contrastive Learning Relies More on Spatial Inductive Bias Than Supervised Learning: An Empirical Study—0
Show:102550
← PrevPage 110 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