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 3701–3750 of 6661 papers

TitleStatusHype
WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal—0
Local Contrastive Learning for Medical Image Recognition—0
Adaptive Similarity Bootstrapping for Self-Distillation based Representation LearningCode0
Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive LearningCode1
Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domains—0
SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology—0
ReVersion: Diffusion-Based Relation Inversion from ImagesCode2
Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection—0
Preventing Dimensional Collapse of Incomplete Multi-View Clustering via Direct Contrastive Learning—0
Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder—0
Multi-view Feature Extraction based on Triple Contrastive Heads—0
CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning—0
Tube-Link: A Flexible Cross Tube Framework for Universal Video SegmentationCode1
Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioning—0
MEDIMP: 3D Medical Images with clinical Prompts from limited tabular data for renal transplantationCode1
MaskCon: Masked Contrastive Learning for Coarse-Labelled DatasetCode1
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationCode0
CLSA: Contrastive Learning-based Survival Analysis for Popularity Prediction in MEC Networks—0
Positive-Augmented Contrastive Learning for Image and Video Captioning EvaluationCode1
Sample4Geo: Hard Negative Sampling For Cross-View Geo-LocalisationCode1
3D-CLFusion: Fast Text-to-3D Rendering with Contrastive Latent Diffusion—0
Debiased Contrastive Learning for Sequential RecommendationCode1
Time Series Contrastive Learning with Information-Aware AugmentationsCode1
ModEFormer: Modality-Preserving Embedding for Audio-Video Synchronization using Transformers—0
Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning—0
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked AutoencodersCode0
Unsupervised Cross-Domain Rumor Detection with Contrastive Learning and Cross-Attention—0
IMF: Interactive Multimodal Fusion Model for Link PredictionCode1
ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning—0
Weakly-Supervised Text Instance Segmentation—0
MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal RepresentationsCode0
Exploring Representation Learning for Small-Footprint Keyword Spotting—0
Learning Audio-Visual Source Localization via False Negative Aware Contrastive LearningCode1
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition—0
STGIC: a graph and image convolution-based method for spatial transcriptomic clustering—0
Reinforcement Learning Friendly Vision-Language Model for MinecraftCode1
Unsupervised Gait Recognition with Selective Fusion—0
HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image SegmentationCode1
Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report GenerationCode1
Denoising Diffusion Autoencoders are Unified Self-supervised LearnersCode1
On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view ClusteringCode1
MassNet: A Deep Learning Approach for Body Weight Extraction from A Single Pressure ImageCode0
Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection—0
SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference—0
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual LearningCode1
All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy ReductionCode0
Unsupervised Facial Expression Representation Learning with Contrastive Local WarpingCode0
Identifiability Results for Multimodal Contrastive LearningCode1
Spherical Space Feature Decomposition for Guided Depth Map Super-ResolutionCode0
Graph-less Collaborative FilteringCode1
Show:102550
← PrevPage 75 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