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 6251–6275 of 6661 papers

TitleStatusHype
Spatiotemporal Contrastive Learning of Facial Expressions in Videos—0
A Low Rank Promoting Prior for Unsupervised Contrastive Learning—0
Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment—0
Semi-weakly Supervised Contrastive Representation Learning for Retinal Fundus ImagesCode0
Control Image Captioning Spatially and Temporally—0
TA-MAMC at SemEval-2021 Task 4: Task-adaptive Pretraining and Multi-head Attention for Abstract Meaning Reading Comprehension—0
xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering—0
Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation—0
On the Efficacy of Small Self-Supervised Contrastive Models without Distillation SignalsCode0
Unsupervised Outlier Detection using Memory and Contrastive Learning—0
DCL: Differential Contrastive Learning for Geometry-Aware Depth SynthesisCode0
Improve Unsupervised Pretraining for Few-label Transfer—0
Revisiting Catastrophic Forgetting in Class Incremental Learning—0
What Remains of Visual Semantic Embeddings—0
The Impact of Negative Sampling on Contrastive Structured World ModelsCode0
Multi-Label Image Classification with Contrastive Learning—0
Improved Text Classification via Contrastive Adversarial Training—0
On the Memorization Properties of Contrastive Learning—0
SMILE: Sparse-Attention based Multiple Instance Contrastive Learning for Glioma Sub-type Classification Using Pathological Image—0
Group Contrastive Self-Supervised Learning on Graphs—0
Compound Figure Separation of Biomedical Images with Side LossCode0
Using system context information to complement weakly labeled data—0
Contrastive Predictive Coding for Anomaly Detection—0
Towards an Interpretable Latent Space in Structured Models for Video Prediction—0
Multi-Level Contrastive Learning for Few-Shot Problems—0
Show:102550
← PrevPage 251 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