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 5451–5475 of 6661 papers

TitleStatusHype
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport DistillationCode1
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video RepresentationCode1
Unsupervised Dense Information Retrieval with Contrastive LearningCode1
CODER: An efficient framework for improving retrieval through COntextual Document Embedding RerankingCode0
Long Context Question Answering via Supervised Contrastive LearningCode0
Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification—0
Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrast—0
Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for RecommendationCode2
Graph Representation Learning via Contrasting Cluster Assignments—0
Bayesian Graph Contrastive Learning—0
Knowledge-Rich Self-Supervision for Biomedical Entity Linking—0
Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning—0
Learning to Retrieve Passages without SupervisionCode1
CLIP-Lite: Information Efficient Visual Representation Learning with Language SupervisionCode1
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
Transferrable Contrastive Learning for Visual Domain Adaptation—0
Semantically Contrastive Learning for Low-light Image EnhancementCode1
Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South Central Andes—0
CT4Rec: Simple yet Effective Consistency Training for Sequential RecommendationCode1
Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-IdentificationCode1
Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness—0
Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry—0
Learning Representations with Contrastive Self-Supervised Learning for Histopathology ApplicationsCode1
A Self-supervised Mixed-curvature Graph Neural Network—0
Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study—0
Show:102550
← PrevPage 219 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