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 2501–2550 of 6661 papers

TitleStatusHype
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving SystemsCode1
A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide GenerationCode1
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action RecognitionCode0
Understanding normalization in contrastive representation learning and out-of-distribution detectionCode0
Joint Self-Supervised and Supervised Contrastive Learning for Multimodal MRI Data: Towards Predicting Abnormal Neurodevelopment—0
Energy-based learning algorithms for analog computing: a comparative studyCode1
A Language-based solution to enable Metaverse RetrievalCode0
Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent RecognitionCode1
Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive LearningCode0
Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQACode1
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision—0
DVIS++: Improved Decoupled Framework for Universal Video SegmentationCode1
Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction—0
CrossBind: Collaborative Cross-Modal Identification of Protein Nucleic-Acid-Binding ResiduesCode0
Coreference Graph Guidance for Mind-Map GenerationCode0
Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context ModelingCode1
Time-Series Contrastive Learning against False Negatives and Class Imbalance—0
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers—0
Chasing Fairness in Graphs: A GNN Architecture PerspectiveCode0
SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action SegmentationCode0
Knowledge Graph Error Detection with Contrastive Confidence AdaptionCode1
Synergistic Anchored Contrastive Pre-training for Few-Shot Relation ExtractionCode0
Object-Aware Domain Generalization for Object DetectionCode1
FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive LearningCode2
Cross-Age Contrastive Learning for Age-Invariant Face Recognition—0
Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor DetectorCode1
Generalized Category Discovery with Large Language Models in the LoopCode1
Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot ResponseCode2
ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide SequencingCode1
The Right Losses for the Right Gains: Improving the Semantic Consistency of Deep Text-to-Image Generation with Distribution-Sensitive Losses—0
SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on TwitterCode1
DER-GCN: Dialogue and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Dialogue Emotion Recognition—0
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion—0
CLDR: Contrastive Learning Drug Response Models from Natural Language SupervisionCode0
Debiasing Multimodal Sarcasm Detection with Contrastive Learning—0
A Soft Contrastive Learning-based Prompt Model for Few-shot Sentiment Analysis—0
STELLAR: Siamese Multi-Headed Attention Neural Networks for Overcoming Temporal Variations and Device Heterogeneity with Indoor LocalizationCode0
ProTIP: Progressive Tool Retrieval Improves Planning—0
Event-Based Contrastive Learning for Medical Time SeriesCode0
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal PerspectiveCode1
CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis—0
Multi-Modality is All You Need for Transferable Recommender SystemsCode1
CETN: Contrast-enhanced Through Network for CTR PredictionCode1
Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound ClassificationCode1
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation ImageryCode3
Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label LearningCode0
Urban Region Embedding via Multi-View Contrastive Prediction—0
CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning—0
Improving Biomedical Entity Linking with Retrieval-enhanced LearningCode0
Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clustering—0
Show:102550
← PrevPage 51 of 134Next →
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