| All | Since 2021 | |
| Citation | 207 | 115 |
| h-index | 7 | 4 |
| i10-index | 2 | 1 |
WJERT Citation Report 
Login
News & Updation
Abstract
DESIGN OF A TRANSFER LEARNING-BASED DEEP LEARNING MODEL FOR DOMAIN-ADAPTIVE CLASSIFICATION
*Pavan Gunda, Tarini Hemanth Kumar, Muppana Sai Karthik, Mada Sai Surya
Venkata Manoj, Lella Naga Sai
ABSTRACT
The goal of developing and using a deep learning model for transferlearning-based domain- adaptive categorization is to addressperformance degradation that occurs when a model trained on onedomain is transferred to a different but related target domain. Thisstrategy lessens the need for huge labeled datasets in the target domainby employing a pretrained convolutional neural network (CNN) as afeature extractor to reuse previously learnt information. By aligningfeature representations through domain adaptation processes, thesystem improves classification performance in a variety of previouslyuntested contexts. Experiments conducted on benchmark datasets shownotable advancements in accuracy and resilience to domain alterations.
[Full Text Article] [Download Certificate] https://doi.org/10.5281/zenodo.19343412