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 51–100 of 6661 papers

TitleStatusHype
I Speak and You Find: Robust 3D Visual Grounding with Noisy and Ambiguous Speech Inputs—0
Refining music sample identification with a self-supervised graph neural networkCode1
Unified Representation Space for 3D Visual Grounding—0
SUSEP-Net: Simulation-Supervised and Contrastive Learning-based Deep Neural Networks for Susceptibility Source Separation—0
RelTopo: Enhancing Relational Modeling for Driving Scene Topology Reasoning—0
TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Scale-Oriented ContrastCode1
Contrastive Self-Supervised Learning As Neural Manifold Packing—0
Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval—0
Quantum-Informed Contrastive Learning with Dynamic Mixup Augmentation for Class-Imbalanced Expert Systems—0
Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and ExplainabilityCode0
Information fusion strategy integrating pre-trained language model and contrastive learning for materials knowledge mining—0
InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning—0
SemanticST: Spatially Informed Semantic Graph Learning for Clustering, Integration, and Scalable Analysis of Spatial Transcriptomics—0
FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition—0
Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust RecommendationCode0
Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning—0
PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image AnalysisCode0
HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data—0
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image ClusteringCode0
On the Similarities of Embeddings in Contrastive LearningCode1
A theoretical framework for self-supervised contrastive learning for continuous dependent data—0
ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory ForecastingCode0
Generalizing Supervised Contrastive learning: A Projection Perspective—0
Probabilistic Variational Contrastive Learning—0
Context-aware TFL: A Universal Context-aware Contrastive Learning Framework for Temporal Forgery Localization—0
Efficient Medical Vision-Language Alignment Through Adapting Masked Vision ModelsCode1
Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning—0
Variational Supervised Contrastive Learning—0
C3S3: Complementary Competition and Contrastive Selection for Semi-Supervised Medical Image SegmentationCode1
Image Reconstruction as a Tool for Feature Analysis—0
Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding—0
Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic GraphsCode0
Multiple Object Stitching for Unsupervised Representation LearningCode1
AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation—0
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive LearningCode0
TRACE: Contrastive learning for multi-trial time-series data in neuroscience—0
Static Word Embeddings for Sentence Semantic Representation—0
Rethinking Contrastive Learning in Session-based RecommendationCode0
CL-ISR: A Contrastive Learning and Implicit Stance Reasoning Framework for Misleading Text Detection on Social Media—0
Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning—0
Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case StudyCode0
Spatiotemporal Contrastive Learning for Cross-View Video Localization in Unstructured Off-road Terrains—0
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained VideosCode0
Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning—0
Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy—0
AuthGuard: Generalizable Deepfake Detection via Language Guidance—0
Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories—0
Weak Supervision for Real World Graphs—0
OpenCarbon: A Contrastive Learning-based Cross-Modality Neural Approach for High-Resolution Carbon Emission Prediction Using Open DataCode0
MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query—0
Show:102550
← PrevPage 2 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