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 5626–5650 of 6661 papers

TitleStatusHype
MixSiam: A Mixture-based Approach to Self-supervised Representation Learning—0
Video Salient Object Detection via Contrastive Features and Attention Modules—0
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive LearningCode1
MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation—0
Contrastive Learning for Context-aware Neural Machine Translation Using Coreference Information—0
Dialogue Response Generation via Contrastive Latent Representation Learning—0
Semi-supervised Intent Discovery with Contrastive Learning—0
Effective Fine-Tuning Methods for Cross-lingual Adaptation—0
Exploring Non-Autoregressive Text Style TransferCode0
KFCNet: Knowledge Filtering and Contrastive Learning for Generative Commonsense Reasoning—0
Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization—0
Counter-Contrastive Learning for Language GANs—0
Grammatical Error Correction with Contrastive Learning in Low Error Density DomainsCode0
Towards the Generalization of Contrastive Self-Supervised LearningCode1
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?Code1
Improving Contrastive Learning on Imbalanced Seed Data via Open-World SamplingCode1
TransAug: Translate as Augmentation for Sentence Embeddings—0
Equivariant Contrastive LearningCode1
RadBERT-CL: Factually-Aware Contrastive Learning For Radiology Report Classification—0
InfoGCL: Information-Aware Graph Contrastive Learning—0
Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction—0
Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing—0
FocusFace: Multi-task Contrastive Learning for Masked Face RecognitionCode1
Graph Communal Contrastive LearningCode0
Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking—0
Show:102550
← PrevPage 226 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