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 6301–6325 of 6661 papers

TitleStatusHype
Cross-Modal Contrastive Learning for Text-to-Image GenerationCode1
Contrastive Learning Improves Critical Event Prediction in COVID-19 Patients—0
Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental ConditionsCode1
GAN-Control: Explicitly Controllable GANsCode1
Representation learning for maximization of MI, nonlinear ICA and nonlinear subspaces with robust density ratio estimation—0
Contrastive Learning for Recommender System—0
Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval—0
Contrastive Learning for Label Efficient Semantic Segmentation—0
Co2L: Contrastive Continual LearningCode1
Pose Invariant Topological Memory for Visual Navigation—0
Rethinking 360deg Image Visual Attention Modelling With Unsupervised Learning.Code0
Learning To Hallucinate Examples From Extrinsic and Intrinsic Supervision—0
Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive LearningCode1
COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language RepresentationCode0
Unsupervised Point Cloud Object Co-Segmentation by Co-Contrastive Learning and Mutual Attention SamplingCode1
Region-Aware Contrastive Learning for Semantic SegmentationCode1
PreDet: Large-Scale Weakly Supervised Pre-Training for Detection—0
Vi2CLR: Video and Image for Visual Contrastive Learning of Representation—0
A Simple Baseline for Weakly-Supervised Scene Graph Generation—0
Contrastive Coding for Active Learning Under Class Distribution Mismatch—0
C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing—0
Learning From Noisy Data With Robust Representation LearningCode1
Noise-Robust Contrastive Learning—0
To Learn Effective Features: Understanding the Task-Specific Adaptation of MAML—0
Self-supervised Temporal Learning—0
Show:102550
← PrevPage 253 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