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 3251–3275 of 6661 papers

TitleStatusHype
Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio DataCode1
Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You NeedCode1
SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification—0
Relation-aware graph structure embedding with co-contrastive learning for drug-drug interaction prediction—0
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases—0
Learning Multi-Agent Communication with Contrastive Learning—0
Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis—0
ENGAGE: Explanation Guided Data Augmentation for Graph Representation LearningCode0
MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information RetrievalCode2
Multiscale Progressive Text Prompt Network for Medical Image Segmentation—0
Multi-network Contrastive Learning Based on Global and Local Representations—0
Subclass-balancing Contrastive Learning for Long-tailed RecognitionCode1
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners—0
GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic SegmentationCode1
Protein-DNA binding sites prediction based on pre-trained protein language model and contrastive learningCode1
Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination methods—0
FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium SegmentationCode0
ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis—0
Unsupervised Episode Generation for Graph Meta-learningCode1
Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning—0
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action LocalizationCode1
PrimeNet: Pre-Training for Irregular Multivariate Time SeriesCode1
Histopathology Image Classification using Deep Manifold Contrastive Learning—0
Contrastive Multi-view Framework for Customer Lifetime Value Prediction—0
A Self-supervised Contrastive Learning Method for Grasp Outcomes Prediction—0
Show:102550
← PrevPage 131 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