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 2951–3000 of 6661 papers

TitleStatusHype
Integrating Deep Metric Learning with Coreset for Active Learning in 3D SegmentationCode0
Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT SegmentationCode0
Interactive Dimensionality Reduction for Comparative AnalysisCode0
Robust Diversified Graph Contrastive Network for Incomplete Multi-view ClusteringCode0
Instance Smoothed Contrastive Learning for Unsupervised Sentence EmbeddingCode0
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object LocalizationCode0
Connect Later: Improving Fine-tuning for Robustness with Targeted AugmentationsCode0
AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video HashingCode0
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation LearningCode0
Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from ImagesCode0
Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source LocalizationCode0
EgoDTM: Towards 3D-Aware Egocentric Video-Language PretrainingCode0
E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic ExpressionsCode0
Incorporating Task-specific Concept Knowledge into Script LearningCode0
Automatic retrieval of corresponding US views in longitudinal examinationsCode0
Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive LearningCode0
Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image SegmentationCode0
Incomplete Contrastive Multi-View Clustering with High-Confidence GuidingCode0
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation LearningCode0
Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor DecompositionCode0
EfficientRec an unlimited user-item scale recommendation system based on clustering and users interaction embedding profileCode0
Efficient Model-Stealing Attacks Against Inductive Graph Neural NetworksCode0
Confidence-aware Contrastive Learning for Selective ClassificationCode0
Contrastive Learning of Sociopragmatic Meaning in Social MediaCode0
Intermediate Domain-guided Adaptation for Unsupervised Chorioallantoic Membrane Vessel SegmentationCode0
Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive LearningCode0
Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation LearningCode0
Cone: Unsupervised Contrastive Opinion ExtractionCode0
Efficient Hierarchical Contrastive Self-supervising Learning for Time Series Classification via Importance-aware Resolution SelectionCode0
Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive LearningCode0
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence PairsCode0
Improving Unsupervised Task-driven Models of Ventral Visual Stream via Relative Position PredictivityCode0
Conditional Supervised Contrastive Learning for Fair Text ClassificationCode0
HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?Code0
Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person SearchCode0
Improving the Robustness of Dense Retrievers Against Typos via Multi-Positive Contrastive LearningCode0
Efficient Cluster-Based k-Nearest-Neighbor Machine TranslationCode0
Conditional Negative Sampling for Contrastive Learning of Visual RepresentationsCode0
Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive LearningCode0
Efficient block contrastive learning via parameter-free meta-node approximationCode0
Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive LearningCode0
Adaptive Contrastive Learning with Dynamic Correlation for Multi-Phase Organ SegmentationCode0
Contrastive Variational Autoencoder Enhances Salient FeaturesCode0
Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language ModelsCode0
Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous DataCode0
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset SelectionCode0
Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?Code0
Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness PredictionsCode0
Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision BoundaryCode0
ConCur: Self-supervised graph representation based on contrastive learning with curriculum negative samplingCode0
Show:102550
← PrevPage 60 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