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 451–500 of 6661 papers

TitleStatusHype
Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data Settings—0
Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context ScenariosCode0
Intermediate Domain-guided Adaptation for Unsupervised Chorioallantoic Membrane Vessel SegmentationCode0
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning—0
Unsupervised Waste Classification By Dual-Encoder Contrastive Learning and Multi-Clustering Voting (DECMCV)—0
X2CT-CLIP: Enable Multi-Abnormality Detection in Computed Tomography from Chest Radiography via Tri-Modal Contrastive Learning—0
V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts—0
FSCIL-SEI: Few-Shot Class-Incremental Learning Approach for Specific Emitter Identification—0
OCL: Ordinal Contrastive Learning for Imputating Features with Progressive Labels—0
Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering—0
Learning Actionable World Models for Industrial Process Control—0
OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-AdjustmentCode0
MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation AlignmentCode0
Random Walks in Self-supervised Learning for Triangular Meshes—0
Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive LearningCode1
Projection Head is Secretly an Information BottleneckCode0
Convergence of energy-based learning in linear resistive networks—0
BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds—0
Discovering Global False Negatives On the Fly for Self-supervised Contrastive LearningCode0
Continuous Adversarial Text Representation Learning for Affective Recognition—0
UoR-NCL at SemEval-2025 Task 1: Using Generative LLMs and CLIP Models for Multilingual Multimodal Idiomaticity RepresentationCode0
Subtask-Aware Visual Reward Learning from Segmented Demonstrations—0
Spatial-Spectral Diffusion Contrastive Representation Network for Hyperspectral Image Classification—0
Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report GenerationCode2
Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion—0
CFTrack: Enhancing Lightweight Visual Tracking through Contrastive Learning and Feature Matching—0
cMIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning—0
Your contrastive learning problem is secretly a distribution alignment problemCode1
Learning Mask Invariant Mutual Information for Masked Image Modeling—0
Adaptive H&E-IHC information fusion staining framework based on feature extraCode0
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data AugmentationCode0
Multiview graph dual-attention deep learning and contrastive learning for multi-criteria recommender systemsCode0
Dictionary-based Framework for Interpretable and Consistent Object Parsing—0
Multi-modal Contrastive Learning for Tumor-specific Missing Modality Synthesis—0
Progressive Local Alignment for Medical Multimodal Pre-training—0
DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers—0
Contrastive Learning with Nasty Noise—0
BRIDO: Bringing Democratic Order to Abstractive Summarization—0
Label-free Prediction of Vascular Connectivity in Perfused Microvascular Networks in vitro—0
CLEP-GAN: An Innovative Approach to Subject-Independent ECG Reconstruction from PPG Signals—0
Supervised contrastive learning from weakly-labeled audio segments for musical version matching—0
VGFL-SA: Vertical Graph Federated Learning Structure Attack Based on Contrastive Learning—0
Snoopy: Effective and Efficient Semantic Join Discovery via Proxy ColumnsCode1
Contrastive Learning of English Language and Crystal Graphs for Multimodal Representation of Materials Knowledge—0
Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition—0
Contrastive Similarity Learning for Market Forecasting: The ContraSim Framework—0
Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling—0
An Autonomous Network Orchestration Framework Integrating Large Language Models with Continual Reinforcement Learning—0
SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-trainingCode1
Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning—0
Show:102550
← PrevPage 10 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