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 15011525 of 6661 papers

TitleStatusHype
Learning 3D Representations of Molecular Chirality with Invariance to Bond RotationsCode1
3D Infomax improves GNNs for Molecular Property PredictionCode1
Phone-to-audio alignment without text: A Semi-supervised ApproachCode1
Temperature as Uncertainty in Contrastive LearningCode1
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot FillingCode1
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source DataCode1
The Information Geometry of Unsupervised Reinforcement LearningCode1
KNN-BERT: Fine-Tuning Pre-Trained Models with KNN ClassifierCode1
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive LearningCode1
Consistent Explanations by Contrastive LearningCode1
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial LearningCode1
Motion-aware Contrastive Video Representation Learning via Foreground-background MergingCode1
Contrastive Label Disambiguation for Partial Label LearningCode1
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillationsCode1
Compressive Visual RepresentationsCode1
DialogueCSE: Dialogue-based Contrastive Learning of Sentence EmbeddingsCode1
Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-IdentificationCode1
Weakly Supervised Contrastive Learning for Chest X-Ray Report GenerationCode1
GeomGCL: Geometric Graph Contrastive Learning for Molecular Property PredictionCode1
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style EditingCode1
AutoGCL: Automated Graph Contrastive Learning via Learnable View GeneratorsCode1
On the Importance of Distractors for Few-Shot ClassificationCode1
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language ModelsCode1
Pointly-supervised 3D Scene Parsing with Viewpoint BottleneckCode1
Self-supervised Contrastive Learning for EEG-based Sleep StagingCode1
Show:102550
← PrevPage 61 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