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 3426–3450 of 6661 papers

TitleStatusHype
Generalizable Synthetic Image Detection via Language-guided Contrastive LearningCode1
Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality—0
Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding—0
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path—0
Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine TranslationCode0
Federated Generalized Category Discovery—0
TaDSE: Template-aware Dialogue Sentence Embeddings—0
EnSiam: Self-Supervised Learning With Ensemble Representations—0
Transfer-Free Data-Efficient Multilingual Slot Labeling—0
Learning Emotion Representations from Verbal and Nonverbal CommunicationCode1
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives—0
Towards Unsupervised Recognition of Token-level Semantic Differences in Related DocumentsCode0
Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine TranslationCode0
Sentence Representations via Gaussian EmbeddingCode0
Registering Neural Radiance Fields as 3D Density Images—0
DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment—0
Open-world Semi-supervised Novel Class DiscoveryCode1
Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID—0
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning—0
Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification—0
From Patches to Objects: Exploiting Spatial Reasoning for Better Visual Representations—0
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical ReasoningCode1
DiffUCD:Unsupervised Hyperspectral Image Change Detection with Semantic Correlation Diffusion Model—0
Low-Entropy Latent Variables Hurt Out-of-Distribution Performance—0
Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection—0
Show:102550
← PrevPage 138 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