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 4276–4300 of 6661 papers

TitleStatusHype
Query-based Instance Discrimination Network for Relational Triple Extraction—0
Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization—0
Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantificationCode0
Latent Prompt Tuning for Text Summarization—0
On the Informativeness of Supervision Signals—0
SLICER: Learning universal audio representations using low-resource self-supervised pre-trainingCode1
Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity—0
Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds—0
Chinese CLIP: Contrastive Vision-Language Pretraining in ChineseCode5
Invariant and consistent: Unsupervised representation learning for few-shot visual recognition—0
Building an Enhanced Autoregressive Document Retriever Leveraging Supervised Contrastive Learning—0
Oracle-guided Contrastive Clustering—0
Position-Aware Subgraph Neural Networks with Data-Efficient LearningCode1
SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking—0
A picture of the space of typical learnable tasksCode1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representationsCode1
Adaptive Speech Quality Aware Complex Neural Network for Acoustic Echo Cancellation with Supervised Contrastive Learning—0
Image-free Domain Generalization via CLIP for 3D Hand Pose Estimation—0
Rare Wildlife Recognition with Self-Supervised Representation LearningCode0
Differentiable Data Augmentation for Contrastive Sentence Representation LearningCode1
Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space—0
Speaker Representation Learning via Contrastive Loss with Maximal Speaker SeparabilityCode1
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest RecommendationCode1
Pair DETR: Contrastive Learning Speeds Up DETR Training—0
Improving the Modality Representation with Multi-View Contrastive Learning for Multimodal Sentiment Analysis—0
Show:102550
← PrevPage 172 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