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 2351–2375 of 6661 papers

TitleStatusHype
Transformer-based Clipped Contrastive Quantization Learning for Unsupervised Image Retrieval—0
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective—0
Incorporating simulated spatial context information improves the effectiveness of contrastive learning models—0
PepGB: Facilitating peptide drug discovery via graph neural networks—0
Challenging Low Homophily in Social Recommendation—0
Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive LearningCode0
Improving Antibody Humanness Prediction using Patent DataCode1
Deep Clustering with Diffused Sampling and Hardness-aware Self-distillationCode0
DenoSent: A Denoising Objective for Self-Supervised Sentence Representation LearningCode1
Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery—0
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level InteractionCode0
Enhancing cross-domain detection: adaptive class-aware contrastive transformer—0
Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype AggregationCode0
Graph Contrastive Invariant Learning from the Causal PerspectiveCode1
DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing—0
Contrastive Learning in Distilled ModelsCode0
Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learning—0
Joint Audio-Visual Attention with Contrastive Learning for More General Deepfake Detection—0
Contrastive Learning and Cycle Consistency-based Transductive Transfer Learning for Target Annotation—0
SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning—0
Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-TrainingCode1
Self-supervised Contrastive Learning for 6G UM-MIMO THz Communications: Improving Robustness Under Imperfect CSI—0
PepHarmony: A Multi-View Contrastive Learning Framework for Integrated Sequence and Structure-Based Peptide EncodingCode0
Visual Imitation Learning with Calibrated Contrastive Representation—0
Unifying Visual and Vision-Language Tracking via Contrastive LearningCode1
Show:102550
← PrevPage 95 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