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 3201–3225 of 6661 papers

TitleStatusHype
GraphCL-DTA: a graph contrastive learning with molecular semantics for drug-target binding affinity prediction—0
Towards the Sparseness of Projection Head in Self-Supervised Learning—0
Contrastive Multi-Task Dense Prediction—0
Neural Architecture RetrievalCode1
Cross-Model Cross-Stream Learning for Self-Supervised Human Action RecognitionCode0
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning—0
AspectCSE: Sentence Embeddings for Aspect-based Semantic Textual Similarity Using Contrastive Learning and Structured Knowledge—0
Semantic Contrastive Bootstrapping for Single-positive Multi-label RecognitionCode0
RegExplainer: Generating Explanations for Graph Neural Networks in Regression TasksCode0
QontSum: On Contrasting Salient Content for Query-focused Summarization—0
Gastrointestinal Disease Classification through Explainable and Cost-Sensitive Deep Neural Networks with Supervised Contrastive LearningCode0
Composition-contrastive Learning for Sentence EmbeddingsCode0
Multi-view self-supervised learning for multivariate variable-channel time seriesCode0
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation—0
Emotion recognition based on multi-modal electrophysiology multi-head attention Contrastive Learning—0
The Whole Pathological Slide Classification via Weakly Supervised Learning—0
Contrastive Learning for Conversion Rate PredictionCode1
Unified Medical Image-Text-Label Contrastive Learning With Continuous Prompt—0
Mini-Batch Optimization of Contrastive LossCode1
Disentangled Contrastive Image Translation for Nighttime Surveillance—0
Class Instance Balanced Learning for Long-Tailed Classification—0
CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction—0
Generative Contrastive Graph Learning for RecommendationCode1
Mao-Zedong At SemEval-2023 Task 4: Label Represention Multi-Head Attention Model With Contrastive Learning-Enhanced Nearest Neighbor Mechanism For Multi-Label Text ClassificationCode0
Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification—0
Show:102550
← PrevPage 129 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