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 5551–5575 of 6661 papers

TitleStatusHype
Mixed Graph Contrastive Network for Semi-Supervised Node Classification—0
Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts—0
Semi-Supervised Learning for Mars Imagery Classification and Segmentation—0
Integrating Prior Knowledge in Contrastive Learning with KernelCode0
Prefix Conditioning Unifies Language and Label Supervision—0
Hard Negative Sampling Strategies for Contrastive Representation Learning—0
Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning—0
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation—0
DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks—0
Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded ViewsCode0
Positive Unlabeled Contrastive Learning—0
Augmentation Component Analysis: Modeling Similarity via the Augmentation OverlapsCode0
Multi-scale frequency separation network for image deblurring—0
Mitigating Dataset Artifacts in Natural Language Inference Through Automatic Contextual Data Augmentation and Learning Optimization—0
Towards Generalisable Audio Representations for Audio-Visual Navigation—0
Generalized Supervised Contrastive Learning—0
From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark DiscoveryCode0
A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference—0
Contrastive Representation Learning for 3D Protein Structures—0
EMS: Efficient and Effective Massively Multilingual Sentence Embedding LearningCode0
CropMix: Sampling a Rich Input Distribution via Multi-Scale CroppingCode0
3D Graph Contrastive Learning for Molecular Property Prediction—0
Contrasting quadratic assignments for set-based representation learningCode0
Pseudo-Data based Self-Supervised Federated Learning for Classification of Histopathological Images—0
Your Contrastive Learning Is Secretly Doing Stochastic Neighbor EmbeddingCode0
Show:102550
← PrevPage 223 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