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 1651–1700 of 6661 papers

TitleStatusHype
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and ClusteringCode1
Towards Cross-Table Masked Pretraining for Web Data MiningCode1
Semantic-Aware Dual Contrastive Learning for Multi-label Image ClassificationCode1
A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect DetectionCode1
Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive LearningCode1
MADGEN: Mass-Spec attends to De Novo Molecular generationCode1
Semi-Supervised Action Recognition with Temporal Contrastive LearningCode1
CL4CTR: A Contrastive Learning Framework for CTR PredictionCode1
Semi-Supervised Contrastive Learning of Musical RepresentationsCode1
CURL: Contrastive Unsupervised Representation Learning for Reinforcement LearningCode1
CURL: Contrastive Unsupervised Representations for Reinforcement LearningCode1
CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive LearningCode1
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little CostCode1
Improving Self-Supervised Learning by Characterizing Idealized RepresentationsCode1
Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure NetworkCode1
SiCL: Silhouette-Driven Contrastive Learning for Unsupervised Person Re-Identification with Clothes ChangeCode1
A Simple Contrastive Learning Objective for Alleviating Neural Text DegenerationCode1
COMPLETER: Incomplete Multi-view Clustering via Contrastive PredictionCode1
Separated Contrastive Learning for Organ-at-Risk and Gross-Tumor-Volume Segmentation with Limited AnnotationCode1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representationsCode1
Sequence-to-Sequence Contrastive Learning for Text RecognitionCode1
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTsCode1
Improving Transformation Invariance in Contrastive Representation LearningCode1
Long-tail Augmented Graph Contrastive Learning for RecommendationCode1
CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive LearningCode1
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance AnnotationCode1
CLAP: Isolating Content from Style through Contrastive Learning with Augmented PromptsCode1
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth LabelsCode1
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little CostCode1
CLARA: Multilingual Contrastive Learning for Audio Representation AcquisitionCode1
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and TextCode1
In-context Contrastive Learning for Event Causality IdentificationCode1
Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text ClassificationCode1
Localizing Visual Sounds the Hard WayCode1
SignCLIP: Connecting Text and Sign Language by Contrastive LearningCode1
A Simple Graph Contrastive Learning Framework for Short Text ClassificationCode1
Inference via Interpolation: Contrastive Representations Provably Enable Planning and InferenceCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
InfoCSE: Information-aggregated Contrastive Learning of Sentence EmbeddingsCode1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
A Simple Long-Tailed Recognition Baseline via Vision-Language ModelCode1
Data Augmenting Contrastive Learning of Speech Representations in the Time DomainCode1
InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive LearningCode1
Low-rank Prompt Interaction for Continual Vision-Language RetrievalCode1
Intent Contrastive Learning with Cross Subsequences for Sequential RecommendationCode1
DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing ModalitiesCode1
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the LeastCode1
A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation ExtractionCode1
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural NetworksCode1
Show:102550
← PrevPage 34 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