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 13011325 of 6661 papers

TitleStatusHype
Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in HistopathologyCode1
Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-IdentificationCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text ClassificationCode1
Contrastive Learning for Prompt-Based Few-Shot Language LearnersCode1
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image ClassificationCode1
Contrastive learning for regression in multi-site brain age predictionCode1
An Efficient Self-Supervised Cross-View Training For Sentence EmbeddingCode1
Contrastive Learning for Representation Degeneration Problem in Sequential RecommendationCode1
Boosting Semi-Supervised Semantic Segmentation with Probabilistic RepresentationsCode1
Self-supervised Spatial Reasoning on Multi-View Line DrawingsCode1
Contrastive Test-Time AdaptationCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Contrastive Learning for Sports Video: Unsupervised Player ClassificationCode1
An Empirical Study on Disentanglement of Negative-free Contrastive LearningCode1
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video RepresentationCode1
Contrastive Learning for Unpaired Image-to-Image TranslationCode1
ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology ImagesCode1
Contrastive Learning for Unsupervised Domain Adaptation of Time SeriesCode1
Hypergraph Contrastive Collaborative FilteringCode1
Hyperspherical Consistency RegularizationCode1
I0T: Embedding Standardization Method Towards Zero Modality GapCode1
iDAG: Invariant DAG Searching for Domain GeneralizationCode1
Identifiability Results for Multimodal Contrastive LearningCode1
Denoise and Contrast for Category Agnostic Shape CompletionCode1
Show:102550
← PrevPage 53 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