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 4301–4350 of 6661 papers

TitleStatusHype
cRedAnno+: Annotation Exploitation in Self-Explanatory Lung Nodule DiagnosisCode1
Pretraining Respiratory Sound Representations using Metadata and Contrastive LearningCode1
Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings—0
Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive LearningCode1
Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction—0
Learning Joint Representation of Human Motion and Language—0
Conversation Disentanglement with Bi-Level Contrastive Learning—0
Dictionary-Assisted Supervised Contrastive LearningCode0
Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs—0
MABEL: Attenuating Gender Bias using Textual Entailment DataCode1
Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing—0
Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts—0
IDEAL: Improved DEnse locAL Contrastive Learning for Semi-Supervised Medical Image SegmentationCode0
Broken Neural Scaling LawsCode1
Meta-node: A Concise Approach to Effectively Learn Complex Relationships in Heterogeneous Graphs—0
Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis—0
Boosting Semi-Supervised Semantic Segmentation with Probabilistic RepresentationsCode1
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and TextCode1
Shared Manifold Learning Using a Triplet Network for Multiple Sensor Translation and Fusion with Missing Data—0
Line Graph Contrastive Learning for Link PredictionCode0
Contrastive Search Is What You Need For Neural Text GenerationCode2
Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical EncodingsCode1
CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation—0
A Chinese Spelling Check Framework Based on Reverse Contrastive Learning—0
Event-Centric Question Answering via Contrastive Learning and Invertible Event TransformationCode0
Contrastive Representation Learning for Gaze EstimationCode1
Heterogeneous Information Crossing on Graphs for Session-based Recommender Systems—0
Non-Contrastive Learning-based Behavioural Biometrics for Smart IoT Devices—0
Adversarial Pretraining of Self-Supervised Deep Networks: Past, Present and Future—0
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddingsCode1
Global Contrastive Batch Sampling via Optimization on Sample PermutationsCode0
Neural Eigenfunctions Are Structured Representation LearnersCode1
Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data AugmentationCode1
A Benchmark Study of Contrastive Learning for Arabic Social MeaningCode0
Exploring Representation-Level Augmentation for Code SearchCode1
Contrastive Prototypical Network with Wasserstein Confidence PenaltyCode1
Multi-View Reasoning: Consistent Contrastive Learning for Math Word ProblemCode2
Twin Contrastive Learning for Online ClusteringCode1
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing—0
GLCC: A General Framework for Graph-Level Clustering—0
BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions)—0
HCL: Improving Graph Representation with Hierarchical Contrastive Learning—0
Visual-Semantic Contrastive Alignment for Few-Shot Image Classification—0
Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem—0
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning—0
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP ModelsCode0
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer EnsembleCode0
SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy GradingCode1
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?Code1
Controller-Guided Partial Label Consistency Regularization with Unlabeled Data—0
Show:102550
← PrevPage 87 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