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 11261150 of 6661 papers

TitleStatusHype
Diagnosing and Rectifying Vision Models using LanguageCode1
Differentiable Data Augmentation for Contrastive Sentence Representation LearningCode1
Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse GranularityCode1
Diffusion-based Contrastive Learning for Sequential RecommendationCode1
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual LearningCode1
A Message Passing Perspective on Learning Dynamics of Contrastive LearningCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Direct Preference-based Policy Optimization without Reward ModelingCode1
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP TrainingCode1
Contrastive Label Disambiguation for Partial Label LearningCode1
Continuous Contrastive Learning for Long-Tailed Semi-Supervised RecognitionCode1
Continuous Learning for Android Malware DetectionCode1
ContraBAR: Contrastive Bayes-Adaptive Deep RLCode1
Contrastive Grouping with Transformer for Referring Image SegmentationCode1
ContraCLM: Contrastive Learning For Causal Language ModelCode1
BankNote-Net: Open dataset for assistive universal currency recognitionCode1
Disentangled Causal Embedding With Contrastive Learning For Recommender SystemCode1
ContraNorm: A Contrastive Learning Perspective on Oversmoothing and BeyondCode1
ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide SequencingCode1
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable BasisCode1
Dissolving Is Amplifying: Towards Fine-Grained Anomaly DetectionCode1
Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information MaximizationCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Contrast and Classify: Training Robust VQA ModelsCode1
CRIS: CLIP-Driven Referring Image SegmentationCode1
Show:102550
← PrevPage 46 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