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 4001–4050 of 6661 papers

TitleStatusHype
Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over TextCode1
Multi-scale multi-modal micro-expression recognition algorithm based on transformer—0
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised LearningCode1
Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations—0
Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST—0
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-TrainingCode1
Learning by Sorting: Self-supervised Learning with Group Ordering ConstraintsCode1
Event Camera Data Pre-training—0
CRADL: Contrastive Representations for Unsupervised Anomaly Detection and Localization—0
MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small DatasetsCode0
Episodes Discovery Recommendation with Multi-Source Augmentations—0
Multi-View Action Recognition Using Contrastive LearningCode0
Graph Contrastive Learning for Multi-omics Data—0
Surveillance Face Anti-spoofing—0
Brain Tissue Segmentation Across the Human Lifespan via Supervised Contrastive Learning—0
Cluster-guided Contrastive Graph Clustering NetworkCode1
Learning Invariance from Generated Variance for Unsupervised Person Re-identificationCode0
SIRL: Similarity-based Implicit Representation Learning—0
A contrastive learning approach for individual re-identification in a wild fish population—0
Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image RetrievalCode1
IntentQA: Context-aware Video Intent ReasoningCode1
iDAG: Invariant DAG Searching for Domain GeneralizationCode1
Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification—0
Scene Graph Contrastive Learning for Embodied Navigation—0
LAC - Latent Action Composition for Skeleton-based Action Segmentation—0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One ClassifierCode0
SGAligner: 3D Scene Alignment with Scene Graphs—0
Enhanced Soft Label for Semi-Supervised Semantic Segmentation—0
CL-MVSNet: Unsupervised Multi-View Stereo with Dual-Level Contrastive LearningCode1
ReactioNet: Learning High-Order Facial Behavior from Universal Stimulus-Reaction by Dyadic Relation Reasoning—0
CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited AnnotationsCode1
Snow Removal in Video: A New Dataset and A Novel MethodCode1
Contrastive Learning Relies More on Spatial Inductive Bias Than Supervised Learning: An Empirical Study—0
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation—0
Semantic Information in Contrastive LearningCode0
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action RecognitionCode0
Unsupervised Video Deraining with An Event CameraCode1
EC2: Emergent Communication for Embodied Control—0
Change-Aware Sampling and Contrastive Learning for Satellite ImagesCode1
WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding—0
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised LearningCode0
Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate LearningCode1
ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via RecyclingCode0
Class Prototypes Based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos—0
Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive LearningCode1
Learning Transformation-Predictive Representations for Detection and Description of Local Features—0
Cross-Domain 3D Hand Pose Estimation With Dual Modalities—0
Difficulty-Based Sampling for Debiased Contrastive Representation Learning—0
Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization—0
CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation—0
Show:102550
← PrevPage 81 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