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 2451–2500 of 6661 papers

TitleStatusHype
Benchmarking Robustness of Contrastive Learning Models for Medical Image-Report Retrieval—0
Advancing Brainwave-Based Biometrics: A Large-Scale, Multi-Session EvaluationCode0
FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing—0
Code and Pixels: Multi-Modal Contrastive Pre-training for Enhanced Tabular Data Analysis—0
Graph Contrastive Learning on Multi-label Classification for Recommendations—0
ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression—0
Robust Single Object Tracking in LiDAR Point Clouds under Adverse Weather Conditions—0
Intent-Interest Disentanglement and Item-Aware Intent Contrastive Learning for Sequential Recommendation—0
Subject Representation Learning from EEG using Graph Convolutional Variational Autoencoders—0
Evaluating unsupervised contrastive learning framework for MRI sequences classification—0
Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning—0
Learning Compact and Robust Representations for Anomaly Detection—0
FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning—0
Multimodal Graph Constrastive Learning and Prompt for ChartQA—0
MedCoDi-M: A Multi-Prompt Foundation Model for Multimodal Medical Data Generation—0
Quantum-inspired Embeddings Projection and Similarity Metrics for Representation LearningCode0
Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive RegressionCode0
Discriminative Representation learning via Attention-Enhanced Contrastive Learning for Short Text ClusteringCode0
VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with LanguageCode0
CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds—0
LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving—0
TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value IdentificationCode0
An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised LearningCode0
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation LearningCode0
Evaluating Image Caption via Cycle-consistent Text-to-Image Generation—0
DarkFarseer: Inductive Spatio-temporal Kriging via Hidden Style Enhancement and Sparsity-Noise Mitigation—0
CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation—0
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views—0
Enhancing Contrastive Learning for Retinal Imaging via Adjusted Augmentation Scales—0
Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding—0
From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning—0
Few-shot Implicit Function Generation via Equivariance—0
Contrastive Learning Augmented Social RecommendationsCode0
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud LearningCode0
Understanding Difficult-to-learn Examples in Contrastive Learning: A Theoretical Framework for Spectral Contrastive Learning—0
An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise—0
Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation—0
ROLL: Robust Noisy Pseudo-label Learning for Multi-View Clustering with Noisy Correspondence—0
ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry StainingCode0
Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation—0
Pay Attention to the Foreground in Object-Centric Learning—0
CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss—0
Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models—0
Less Attention is More: Prompt Transformer for Generalized Category DiscoveryCode0
A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets—0
Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation—0
SKE-Layout: Spatial Knowledge Enhanced Layout Generation with LLMs—0
Perceptual Inductive Bias Is What You Need Before Contrastive Learning—0
Multi-modal Contrastive Learning with Negative Sampling Calibration for Phenotypic Drug Discovery—0
V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts—0
Show:102550
← PrevPage 50 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