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 5051–5100 of 6661 papers

TitleStatusHype
Mitigating Negative Style Transfer in Hybrid Dialogue SystemCode0
Establishing a stronger baseline for lightweight contrastive modelsCode0
Tailoring Visual Object Representations to Human Requirements: A Case Study with a Recycling RobotCode0
Boosting Semi-Supervised Learning with Contrastive Complementary Labeling—0
A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps—0
Generative artificial intelligence-enabled dynamic detection of nicotine-related circuits—0
Coarse-to-Fine Contrastive Learning on Graphs—0
Momentum Contrastive Pre-training for Question Answering—0
Feature-Level Debiased Natural Language UnderstandingCode0
Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor DecompositionCode0
Using Multiple Instance Learning to Build Multimodal Representations—0
Self-Supervised Object Goal Navigation with In-Situ Finetuning—0
Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection—0
MED-SE: Medical Entity Definition-based Sentence Embedding—0
Localized Contrastive Learning on Graphs—0
SimVTP: Simple Video Text Pre-training with Masked AutoencodersCode0
Unsupervised Flood Detection on SAR Time Series—0
GraphLearner: Graph Node Clustering with Fully Learnable AugmentationCode0
Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty—0
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations—0
Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation—0
Location-Aware Self-Supervised Transformers for Semantic Segmentation—0
Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning—0
Few-Shot Nested Named Entity Recognition—0
Spectral Feature Augmentation for Graph Contrastive Learning and Beyond—0
3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation—0
Self-supervised On-device Federated Learning from Unlabeled Streams—0
A General Purpose Supervisory Signal for Embodied Agents—0
One-shot recognition of any material anywhere using contrastive learning with physics-based renderingCode0
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical LearningCode0
Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View—0
An Effective Deployment of Contrastive Learning in Multi-label Text Classification—0
GENNAPE: Towards Generalized Neural Architecture Performance EstimatorsCode0
FIESTA: Autoencoders for accurate fiber segmentation in tractography—0
Textual Enhanced Contrastive Learning for Solving Math Word ProblemsCode0
ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness—0
Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene UnderstandingCode0
A Theoretical Study of Inductive Biases in Contrastive Learning—0
A Knowledge-based Learning Framework for Self-supervised Pre-training Towards Enhanced Recognition of Biomedical Microscopy ImagesCode0
A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix—0
Towards Better Document-level Relation Extraction via Iterative InferenceCode0
Supervised Contrastive Prototype Learning: Augmentation Free Robust Neural Network—0
A Semi-supervised Learning Approach for B-line Detection in Lung Ultrasound Images—0
Link Prediction with Non-Contrastive LearningCode0
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene SegmentationCode0
Cross-domain Transfer of defect features in technical domains based on partial target data—0
Graph Contrastive Learning for Materials—0
Contrastive pretraining for semantic segmentation is robust to noisy positive pairs—0
Few-shot Object Detection with Refined Contrastive Learning—0
Prototypical Contrastive Learning and Adaptive Interest Selection for Candidate Generation in Recommendations—0
Show:102550
← PrevPage 102 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