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 2676–2700 of 6661 papers

TitleStatusHype
Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual AlignmentCode0
Improving Hateful Meme Detection through Retrieval-Guided Contrastive LearningCode1
Contrastive Learning for Multi-Object Tracking with TransformersCode0
Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning—0
TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition—0
CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal ConversionCode1
Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image RetrievalCode0
AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection—0
Towards Automatic Honey Bee Flower-Patch Assays with Paint Marking Re-Identification—0
CL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection—0
Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition—0
Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding—0
Advancing Drug Discovery with Enhanced Chemical Understanding via Asymmetric Contrastive Multimodal LearningCode0
Visual Commonsense based Heterogeneous Graph Contrastive Learning—0
TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree TransformationCode0
Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking—0
ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation—0
Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samples—0
Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-CollapseCode0
Self-similarity Prior Distillation for Unsupervised Remote Physiological MeasurementCode1
Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks—0
Towards a Unified Framework of Contrastive Learning for Disentangled Representations—0
Learning Discriminative Features for Crowd Counting—0
Unifying Structure and Language Semantic for Efficient Contrastive Knowledge Graph Completion with Structured Entity Anchors—0
Sparse Contrastive Learning of Sentence Embeddings—0
Show:102550
← PrevPage 108 of 267Next →
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