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 4901–4925 of 6661 papers

TitleStatusHype
Unsupervised learning of features and object boundaries from local prediction—0
Bayesian Robust Graph Contrastive LearningCode0
Image Harmonization with Region-wise Contrastive Learning—0
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
Learning Dialogue Representations from Consecutive UtterancesCode1
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation—0
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial LearningCode1
Triangular Contrastive Learning on Molecular Graphs—0
Target-aware Abstractive Related Work Generation with Contrastive LearningCode1
Cross-Architecture Self-supervised Video Representation LearningCode1
Fine-grained Contrastive Learning for Relation ExtractionCode0
Optimizing Test-Time Query Representations for Dense RetrievalCode1
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation—0
Interaction of a priori Anatomic Knowledge with Self-Supervised Contrastive Learning in Cardiac Magnetic Resonance Imaging—0
Contrastive Learning with Boosted MemorizationCode1
New Intent Discovery with Pre-training and Contrastive LearningCode1
RecipeRec: A Heterogeneous Graph Learning Model for Recipe RecommendationCode0
An Adaptive Contrastive Learning Model for Spike Sorting—0
SCVRL: Shuffled Contrastive Video Representation Learning—0
Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities—0
ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification—0
Conditional Supervised Contrastive Learning for Fair Text ClassificationCode0
Multi-Temporal Spatial-Spectral Comparison Network for Hyperspectral Anomalous Change Detection—0
GraphMAE: Self-Supervised Masked Graph AutoencodersCode2
Contrastive Learning of Coarse-Grained Force Fields—0
Show:102550
← PrevPage 197 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