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 4101–4150 of 6661 papers

TitleStatusHype
Masked autoencoders are effective solution to transformer data-hungryCode1
ALSO: Automotive Lidar Self-supervision by Occupancy estimationCode1
Momentum Contrastive Pre-training for Question Answering—0
Using Multiple Instance Learning to Build Multimodal Representations—0
Feature-Level Debiased Natural Language UnderstandingCode0
Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the DefenseCode1
YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure SegmentationCode1
Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor DecompositionCode0
Transductive Linear Probing: A Novel Framework for Few-Shot Node ClassificationCode1
MED-SE: Medical Entity Definition-based Sentence Embedding—0
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive LearningCode1
Self-Supervised Object Goal Navigation with In-Situ Finetuning—0
Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection—0
Localized Contrastive Learning on Graphs—0
Graph Matching with Bi-level Noisy CorrespondenceCode1
Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive LearningCode1
GraphLearner: Graph Node Clustering with Fully Learnable AugmentationCode0
Unsupervised Flood Detection on SAR Time Series—0
SimVTP: Simple Video Text Pre-training with Masked AutoencodersCode0
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations—0
Neural Machine Translation with Contrastive Translation MemoriesCode1
Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty—0
InternVideo: General Video Foundation Models via Generative and Discriminative LearningCode4
Location-Aware Self-Supervised Transformers for Semantic Segmentation—0
Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation—0
Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning—0
Contrastive Domain Adaptation for Time-Series via Temporal MixupCode1
MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time SeriesCode1
3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation—0
Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive AlignmentCode1
Self-supervised On-device Federated Learning from Unlabeled Streams—0
Few-Shot Nested Named Entity Recognition—0
Spectral Feature Augmentation for Graph Contrastive Learning and Beyond—0
A General Purpose Supervisory Signal for Embodied Agents—0
An Effective Deployment of Contrastive Learning in Multi-label Text Classification—0
Hyperbolic Contrastive Learning for Visual Representations beyond ObjectsCode1
Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View—0
One-shot recognition of any material anywhere using contrastive learning with physics-based renderingCode0
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical LearningCode0
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text PairsCode1
CL4CTR: A Contrastive Learning Framework for CTR PredictionCode1
Normalized Contrastive Learning for Text-Video RetrievalCode1
FIESTA: Autoencoders for accurate fiber segmentation in tractography—0
GENNAPE: Towards Generalized Neural Architecture Performance EstimatorsCode0
Textual Enhanced Contrastive Learning for Solving Math Word ProblemsCode0
PLA: Language-Driven Open-Vocabulary 3D Scene UnderstandingCode2
Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic SegmentationCode2
ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness—0
Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene UnderstandingCode0
A Theoretical Study of Inductive Biases in Contrastive Learning—0
Show:102550
← PrevPage 83 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