Wu, Xiaoping, Zhan, Chi, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Ming-Ming, Cheng and Yang, Jufeng 2019. IP102: A large-scale benchmark dataset for insect pest recognition. Presented at: CVPR 2019, Long Beach, CA, USA, 16-20 June 2019. |
Preview |
PDF
- Accepted Post-Print Version
Download (2MB) | Preview |
Abstract
Insect pests are one of the main factors affecting agricultural product yield. Accurate recognition of insect pests facilitates timely preventive measures to avoid economic losses. However, the existing datasets for the visual classification task mainly focus on common objects, e.g., flowers and dogs. This limits the application of powerful deep learning technology on specific domains like the agricultural field. In this paper, we collect a large-scale dataset named IP102 for insect pest recognition. Specifically, it contains more than 75,000 images belonging to 102 categories, which exhibit a natural long-tailed distribution. In addition, we annotate about 19, 000 images with bounding boxes for object detection. The IP102 has a hierarchical taxonomy and the insect pests which mainly affect one specific agricultural product are grouped into the same upper level category. Furthermore, we perform several baseline experiments on the IP102 dataset, including handcrafted and deep feature based classification methods. Experimental results show that this dataset has the challenges of interand intra- class variance and data imbalance. We believe our IP102 will facilitate future research on practical insect pest control, fine-grained visual classification, and imbalanced learning fields. We make the dataset and pre-trained models publicly available at https://github.com/ xpwu95/IP102
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Acceptance |
Status: | Unpublished |
Schools: | Computer Science & Informatics |
Related URLs: | |
Date of First Compliant Deposit: | 5 April 2019 |
Date of Acceptance: | 11 March 2019 |
Last Modified: | 25 Oct 2022 14:05 |
URI: | https://orca.cardiff.ac.uk/id/eprint/121533 |
Citation Data
Cited 253 times in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
Edit Item |