Exploring Fine-Grained Feature Analysis for Bird Species Classification using Layer-wise Relevance Propagation

This research investigates fine-grained feature analysis in bird species classification using the CUB-200-2011 dataset, specifically focusing on Layer-wise Relevance Propagation (LRP). The dataset's annotated bounding boxes and part annotations offer a unique opportunity to explore the contribu...

Full description

Saved in:

Bibliographic Details
Published in:	2024 IEEE World AI IoT Congress (AIIoT) pp. 625 - 631
Main Authors:	Arquilla, Kyle, Gajera, Ishan Dilipbhai, Darling, Melanie, Bhati, Deepshikha, Singh, Aditi, Guercio, Angela
Format:	Conference Proceeding
Language:	English
Published:	IEEE 29-05-2024
Subjects:	Analytical models Deep learning Feature localization FGVC Focusing Image color analysis Interpretability LRP Neural networks Semantics Shape Visual explanations Visualization
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This research investigates fine-grained feature analysis in bird species classification using the CUB-200-2011 dataset, specifically focusing on Layer-wise Relevance Propagation (LRP). The dataset's annotated bounding boxes and part annotations offer a unique opportunity to explore the contribution of intricate details in categorizing bird species. We propose tailored LRP models to effectively analyze fine-grained features in bird images. Our study involves an in-depth feature attribution analysis using LRP to elucidate the neural network models' decision-making process. We aim to identify the features or parts of bird images that play a significant role in classification, thereby providing insights into the discriminative aspects crucial for accurate categorization. Through LRP techniques, we localize and high-light discriminative features within bird images, such as feather patterns, shapes, or colors, contributing to the advancement of fine-grained classification in ornithology.
DOI:	10.1109/AIIoT61789.2024.10579007