ItemConference Paper

Enhanced Image Classification using Transfer Learning with ResNet50-V2: A Case Study on Wildlife Recognition

Title
Enhanced Image Classification using Transfer Learning with ResNet50-V2: A Case Study on Wildlife Recognition
Creator
Chandan, N.; Manimekala, B.; Siva Balan, R.V.
Description
This study explores the application of transfer learning using the ResNet50-V2 architecture for accurate classification of Arctic wildlife species, including Arctic foxes, polar bears, and walruses. Transfer learning leverages pretrained networks to enhance performance in new tasks with limited labeled data, reducing the need for extensive data collection and computational resources. In this work, we utilized a dataset of 1000 labeled images across the three species and applied ResNet50-V2, pre-trained on ImageNet, as a feature extractor. The model achieved high accuracy, with training and validation accuracies nearing 99% and 95-97%, respectively, though minor overfitting was observed. This indicates the model's strong ability to generalize across the dataset while benefiting from pre-trained weights on diverse, non-related images. Additionally it compares with models like SSD and CycleGAN, emphasizing its capability to generalize well, handle small datasets, and mitigate overfitting. We discuss model architecture, data preprocessing, and the experimental results, focusing on improvements achievable through regularization techniques to counteract overfitting. This study demonstrates the effectiveness of transfer learning for wildlife classification, providing insights into optimizing CNNs for ecological and conservation applications. 2025 IEEE.
Source
6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025 - Proceedings;pp.1565-1570
Date
01-01-2025
Publisher
Institute of Electrical and Electronics Engineers Inc.
Subject
CNN; CycleGAN; Model Selection; ResNet50-V2; Transfer Learning; wildlife classification
Coverage
Chandan N., Department of Computer Science, CHRIST (Deemed to be University), Yeshwanthpur Campus, Karnataka, Bangalore, 560073, India; Manimekala B., Department of Computer Science, CHRIST (Deemed to be University), Yeshwanthpur Campus, Karnataka, Bangalore, 560073, India; Siva Balan R.V., Department of Computer Science, CHRIST (Deemed to be University), Yeshwanthpur Campus, Karnataka, Bangalore, 560073, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISBN: 979-833152266-7;
Format
online
Language
English
Type
Conference paper

Citation

Chandan, N.; Manimekala, B.; Siva Balan, R.V., “Enhanced Image Classification using Transfer Learning with ResNet50-V2: A Case Study on Wildlife Recognition,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 17, 2026, https://archives.christuniversity.in/items/show/26056.

Output Formats