SOTAVerified

Transfer Learning

Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.

( Image credit: Subodh Malgonde )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4801–4825 of 10307 papers

TitleStatusHype
L-HYDRA: Multi-Head Physics-Informed Neural NetworksCode0
ANNA: Abstractive Text-to-Image Synthesis with Filtered News CaptionsCode0
Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB — retrained AlexNet convolutional neural networkCode0
Reduced Deep Convolutional Activation Features (R-DeCAF) in Histopathology Images to Improve the Classification Performance for Breast Cancer Diagnosis—0
A Survey on Deep Industrial Transfer Learning in Fault Prognostics—0
Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)—0
Finding the Most Transferable Tasks for Brain Image Segmentation—0
Holistic Multi-Slice Framework for Dynamic Simultaneous Multi-Slice MRI Reconstruction—0
Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling—0
Transfer Learning for Classification of Alzheimer's Disease Based on Genome Wide Data—0
Transferable Energy Storage Bidder—0
Towards Universal LiDAR-Based 3D Object Detection by Multi-Domain Knowledge Transfer—0
Troubleshooting Ethnic Quality Bias with Curriculum Domain Adaptation for Face Image Quality AssessmentCode0
Weak-Shot Object Detection Through Mutual Knowledge Transfer—0
TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition—0
SkeleTR: Towards Skeleton-based Action Recognition in the Wild—0
COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport—0
Robust Heterogeneous Federated Learning under Data CorruptionCode0
Unleashing the Power of Shared Label Structures for Human Activity Recognition—0
Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation—0
Guided Recommendation for Model Fine-Tuning—0
LAC - Latent Action Composition for Skeleton-based Action Segmentation—0
Quality Diversity for Visual Pre-Training—0
SSDA: Secure Source-Free Domain AdaptationCode0
DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning—0
Show:102550
← PrevPage 193 of 413Next →
All datasetsOffice-Home100 sleep nights of 8 caregiversBanglaLekha Isolated DatasetCOCO70KITTI Object Tracking Evaluation 2012Retinal Fundus MultiDisease Image Dataset (RFMiD)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1APCLIPAccuracy84.2—Unverified
2DFA-ENTAccuracy69.2—Unverified
3DFA-SAFNAccuracy69.1—Unverified
4EasyTLAccuracy63.3—Unverified
5MEDAAccuracy60.3—Unverified
#ModelMetricClaimedVerifiedStatus
1CNN10-20% Mask PSNR3.23—Unverified
#ModelMetricClaimedVerifiedStatus
1Chatterjee, Dutta et al.[1]Accuracy96.12—Unverified
#ModelMetricClaimedVerifiedStatus
1Co-TuningAccuracy85.65—Unverified
#ModelMetricClaimedVerifiedStatus
1Physical AccessEER5.74—Unverified
#ModelMetricClaimedVerifiedStatus
1riadd.aucmediAUROC0.95—Unverified