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 3576–3600 of 6661 papers

TitleStatusHype
Stock Recommendations for Individual Investors: A Temporal Graph Network Approach with Mean-Variance Efficient Sampling—0
Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP)—0
Deep Fusion: Capturing Dependencies in Contrastive Learning via Transformer Projection Heads—0
To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning—0
NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification—0
Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection—0
Cross-lingual Contextualized Phrase RetrievalCode0
Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation LearningCode0
CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification—0
CLHA: A Simple yet Effective Contrastive Learning Framework for Human AlignmentCode0
Joint enhancement of automatic chest X-ray diagnosis and radiological gaze prediction with multi-stage cooperative learning—0
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning—0
Knowledge-aware Dual-side Attribute-enhanced RecommendationCode0
Toward Open-Set Human Object Interaction DetectionCode0
EG-ConMix: An Intrusion Detection Method based on Graph Contrastive Learning—0
Multi-Scale Spatio-Temporal Graph Convolutional Network for Facial Expression Spotting—0
Towards Channel-Resilient CSI-Based RF Fingerprinting using Deep Learning—0
EAGLE: A Domain Generalization Framework for AI-generated Text Detection—0
Contrastive Learning on Multimodal Analysis of Electronic Health Records—0
Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations—0
FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos—0
CTSM: Combining Trait and State Emotions for Empathetic Response ModelCode0
Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation—0
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential RecommendationCode0
Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks—0
Show:102550
← PrevPage 144 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