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 4976–5000 of 6661 papers

TitleStatusHype
UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive LearningCode1
HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation ExtractionCode1
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training—0
Do More Negative Samples Necessarily Hurt in Contrastive Learning?—0
i-Code: An Integrative and Composable Multimodal Learning Framework—0
Contrastive Learning for Prompt-Based Few-Shot Language LearnersCode1
Attention-wise masked graph contrastive learning for predicting molecular property—0
Debiased Contrastive Learning of Unsupervised Sentence RepresentationsCode1
Knowledge Graph Contrastive Learning for RecommendationCode1
Contrastive Learning for Improving ASR Robustness in Spoken Language UnderstandingCode1
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation—0
Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification—0
A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular Space—0
GL-CLeF: A Global–Local Contrastive Learning Framework for Cross-lingual Spoken Language UnderstandingCode0
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive LearningCode1
Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource LanguagesCode0
KNN-Contrastive Learning for Out-of-Domain Intent Classification—0
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little CostCode1
Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training—0
Syntax-guided Contrastive Learning for Pre-trained Language Model—0
Mitigating Contradictions in Dialogue Based on Contrastive Learning—0
Controlled Text Generation Using Dictionary Prior in Variational Autoencoders—0
When does CLIP generalize better than unimodal models? When judging human-centric concepts—0
Utilizing Cross-Modal Contrastive Learning to Improve Item Categorization BERT Model—0
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance DetectionCode1
Show:102550
← PrevPage 200 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