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 2101–2150 of 6661 papers

TitleStatusHype
Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval—0
Lifelong Person Re-Identification with Backward-Compatibility—0
What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent PerceptionCode0
Computer User Interface Understanding. A New Dataset and a Learning Framework—0
Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning—0
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic GraspingCode2
Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality—0
Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization—0
Counterfactual contrastive learning: robust representations via causal image synthesisCode1
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D UnderstandingCode1
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive LearningCode1
Anatomical Structure-Guided Medical Vision-Language Pre-training—0
Hyper-CL: Conditioning Sentence Representations with HypernetworksCode1
Dyadic Interaction Modeling for Social Behavior GenerationCode1
CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow—0
MolBind: Multimodal Alignment of Language, Molecules, and Proteins—0
Deep Submodular Peripteral Networks—0
When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?—0
Deep-learning-based clustering of OCT images for biomarker discovery in age-related macular degeneration (Pinnacle study report 4)—0
Self-supervised Contrastive Learning for Implicit Collaborative Filtering—0
Disentangling Policy from Offline Task Representation Learning via Adversarial Data AugmentationCode0
LLMvsSmall Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model—0
Spatiotemporal Representation Learning for Short and Long Medical Image Time SeriesCode0
A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing ModelsCode0
Calibrating Multi-modal Representations: A Pursuit of Group Robustness without AnnotationsCode0
Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning—0
Intra-video Positive Pairs in Self-Supervised Learning for UltrasoundCode0
Learn and Search: An Elegant Technique for Object Lookup using Contrastive Learning—0
Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation—0
Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models—0
TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance—0
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations—0
Multi-modal Semantic Understanding with Contrastive Cross-modal Feature AlignmentCode0
Exploiting Style Latent Flows for Generalizing Deepfake Video Detection—0
Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive LearningCode1
Decoupled Contrastive Learning for Long-Tailed RecognitionCode1
Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning—0
Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification—0
Deep Contrastive Multi-view Clustering under Semantic Feature Guidance—0
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning—0
Text-to-Audio Generation Synchronized with Videos—0
Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter ProfileCode0
ContrastDiagnosis: Enhancing Interpretability in Lung Nodule Diagnosis Using Contrastive Learning—0
Poly-View Contrastive Learning—0
Enhancing Multimodal Unified Representations for Cross Modal Generalization—0
Self-Adapting Large Visual-Language Models to Edge Devices across Visual ModalitiesCode1
Control-based Graph Embeddings with Data Augmentation for Contrastive Learning—0
UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed EntitiesCode0
ACC-ViT : Atrous Convolution's Comeback in Vision Transformers—0
Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global WorkspaceCode0
Show:102550
← PrevPage 43 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