A Method for Enhancing the Accuracy of Pet Breeds Identification Model in Complex Environments-Reference-Cited by-同舟云学术

A Method for Enhancing the Accuracy of Pet Breeds Identification Model in Complex Environments

Published:2024-08-07 Issue:16 Volume:14 Page:6914
ISSN:2076-3417
Container-title:Applied Sciences
language:en
Short-container-title:Applied Sciences

Author:

Lin Zhonglan¹,Xia Haiying¹^ORCID,Liu Yan¹,Qin Yunbai¹^ORCID,Wang Cong¹

Affiliation:

1. School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, China

Abstract

Most existing studies on pet breeds classification focus on images with simple backgrounds, leading to the unsatisfactory performance of models in practical applications. This paper investigates training pet breeds classification models using complex images and constructs a dataset for identifying breeds of pet cats and dogs. We use this dataset to fine-tune three SOTA models: ResNet34, DenseNet121, and Swin Transformer. Specifically, in terms of top-1 accuracy, the performance of DenseNet is improved from 89.10% to 89.19%, while that of the Swin Transformer is increased by 1.26%, marking the most significant enhancement. The results show that training with our dataset significantly enhances the models’ classification capabilities in complex environments. Additionally, we offer a lightweight pet breeds identification model based on PBI-EdgeNeXt (Pet Breeds Identification EdgeNeXt). We utilizes the PolyLoss function and Sophia optimizer for model training. Furthermore, we compare our model with five commonly used lightweight models and find that the proposed model achieves the highest top-1 accuracy of 87.12%. These results demonstrate that the model achieves high accuracy, reaching the SOTA level.

Publisher

MDPI AG

Link

https://www.mdpi.com/2076-3417/14/16/6914/pdf

Reference36 articles.

1. Forensic DNA phenoty**: Canis familiaris breed classification and skeletal phenotype prediction using functionally significant skeletal SNPs and indels;Raymond;Anim. Genet.,2022

2. Imagenet classification with deep convolutional neural networks;Krizhevsky;Adv. Neural Inf. Process. Syst.,2012

3. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.

4. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany. proceedings, part III 18.

5. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv.