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 1401–1450 of 6661 papers

TitleStatusHype
Contrastive Learning with Hard Negative Entities for Entity Set ExpansionCode1
Contrastive Learning with Hard Negative SamplesCode1
Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy DetectionCode1
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical ReasoningCode1
In-N-Out Generative Learning for Dense Unsupervised Video SegmentationCode1
Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrievalCode1
Enhancing Sound Source Localization via False Negative EliminationCode1
Enriched Music Representations with Multiple Cross-modal Contrastive LearningCode1
Expanding Low-Density Latent Regions for Open-Set Object DetectionCode1
Contrastive Learning with Stronger AugmentationsCode1
Contrastive Learning with Synthetic PositivesCode1
Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language ModelsCode1
Inference via Interpolation: Contrastive Representations Provably Enable Planning and InferenceCode1
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling CasesCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningCode1
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive LearningCode1
Equivariant Contrastive LearningCode1
EraseAnything: Enabling Concept Erasure in Rectified Flow TransformersCode1
Contrastive Mean Teacher for Domain Adaptive Object DetectorsCode1
Contrastive Meta Learning with Behavior Multiplicity for RecommendationCode1
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic SegmentationCode1
Contrastive Test-Time AdaptationCode1
Broken Neural Scaling LawsCode1
PITN: Physics-Informed Temporal Networks for Cuffless Blood Pressure EstimationCode1
InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic PerspectiveCode1
Evaluating Modules in Graph Contrastive LearningCode1
Multi-level Feature Learning for Contrastive Multi-view ClusteringCode1
Contrastive Multimodal Fusion with TupleInfoNCECode1
EulerFormer: Sequential User Behavior Modeling with Complex Vector AttentionCode1
Compositional Exemplars for In-context LearningCode1
Indiscriminate Poisoning Attacks on Unsupervised Contrastive LearningCode1
Contrastive Multiview CodingCode1
Neural Machine Translation with Contrastive Translation MemoriesCode1
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive LearningCode1
CoLES: Contrastive Learning for Event Sequences with Self-SupervisionCode1
InfoCSE: Information-aggregated Contrastive Learning of Sentence EmbeddingsCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex InteractionsCode1
Contrastive Object-level Pre-training with Spatial Noise Curriculum LearningCode1
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural NetworksCode1
Contrastive Positive Sample Propagation along the Audio-Visual Event LineCode1
CT4Rec: Simple yet Effective Consistency Training for Sequential RecommendationCode1
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive LearningCode1
Self-supervised Spatial Reasoning on Multi-View Line DrawingsCode1
Contrastive Learning for Sequential RecommendationCode1
Adversarial Contrastive Learning via Asymmetric InfoNCECode1
Contrastive Vision-Language Alignment Makes Efficient Instruction LearnerCode1
Show:102550
← PrevPage 29 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