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 3476–3500 of 6661 papers

TitleStatusHype
UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive LearningCode1
UOR: Universal Backdoor Attacks on Pre-trained Language Models—0
Learning Better Contrastive View from Radiologist's GazeCode1
Improved baselines for vision-language pre-training—0
Masked Collaborative Contrast for Weakly Supervised Semantic SegmentationCode0
Latent Processes Identification From Multi-View Time SeriesCode0
RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-trainingCode0
Instance Smoothed Contrastive Learning for Unsupervised Sentence EmbeddingCode0
Visual Information Extraction in the Wild: Practical Dataset and End-to-end SolutionCode1
Learning the Visualness of Text Using Large Vision-Language Models—0
Masked Audio Text Encoders are Effective Multi-Modal Rescorers—0
Deep Multi-View Subspace Clustering with Anchor GraphCode1
GCFAgg: Global and Cross-view Feature Aggregation for Multi-view ClusteringCode1
Continual Vision-Language Representation Learning with Off-Diagonal Information—0
Serial Contrastive Knowledge Distillation for Continual Few-shot Relation ExtractionCode1
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision TransformersCode1
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild—0
Dynamic Graph Representation Learning for Depression Screening with Transformer—0
Self-Supervised Video Representation Learning via Latent Time Navigation—0
Inclusive FinTech Lending via Contrastive Learning and Domain Adaptation—0
Weakly-supervised ROI extraction method based on contrastive learning for remote sensing imagesCode0
Towards Effective Visual Representations for Partial-Label LearningCode1
Unsupervised Dense Retrieval Training with Web AnchorsCode0
Learning Semi-supervised Gaussian Mixture Models for Generalized Category DiscoveryCode1
iEdit: Localised Text-guided Image Editing with Weak Supervision—0
Show:102550
← PrevPage 140 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