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

Showing 18011825 of 6661 papers

TitleStatusHype
MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray ModelsCode1
Contrastive Learning with Hard Negative SamplesCode1
Representation Learning for Sequence Data with Deep Autoencoding Predictive ComponentsCode1
Unsupervised Representation Learning by InvariancePropagationCode1
Unsupervised Reference-Free Summary Quality Evaluation via Contrastive LearningCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Hard Negative Mixing for Contrastive LearningCode1
Joint Contrastive Learning with Infinite PossibilitiesCode1
Driver Anomaly Detection: A Dataset and Contrastive Learning ApproachCode1
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
Label-Efficient Multi-Task Segmentation using Contrastive LearningCode1
Contrastive ClusteringCode1
DVG-Face: Dual Variational Generation for Heterogeneous Face RecognitionCode1
A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect DetectionCode1
MoPro: Webly Supervised Learning with Momentum PrototypesCode1
Group-wise Contrastive Learning for Neural Dialogue GenerationCode1
Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual LocalizationCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral ClassificationCode1
Active Contrastive Learning of Audio-Visual Video RepresentationsCode1
VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment RetrievalCode1
Self-supervised Video Representation Learning by Pace PredictionCode1
Spatiotemporal Contrastive Video Representation LearningCode1
Unsupervised Feature Learning by Cross-Level Instance-Group DiscriminationCode1
Show:102550
← PrevPage 73 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified