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 5701–5725 of 6661 papers

TitleStatusHype
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation LearningCode0
CoCoSoDa: Effective Contrastive Learning for Code Search—0
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations—0
Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency—0
Detail-recovery Image Deraining via Dual Sample-augmented Contrastive LearningCode0
Hierarchical Self-supervised Representation Learning for Movie Understanding—0
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations—0
A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition—0
Transient motion classification through turbid volumes via parallelized single-photon detection and deep contrastive embedding—0
Estimating Fine-Grained Noise Model via Contrastive Learning—0
Bayesian Negative Sampling for RecommendationCode0
A Dual-Contrastive Framework for Low-Resource Cross-Lingual Named Entity RecognitionCode0
Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks—0
Transformer-Empowered Content-Aware Collaborative Filtering—0
CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment AnalysisCode0
Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt TuningCode0
CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection—0
Marginal Contrastive Correspondence for Guided Image Generation—0
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation—0
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval—0
Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning—0
Self-distillation Augmented Masked Autoencoders for Histopathological Image Classification—0
How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning—0
Controllable Augmentations for Video Representation Learning—0
Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended VersionCode0
Show:102550
← PrevPage 229 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