IP102

by Xiaoping Wu1,Chi Zhan1,Yu-Kun Lai2,Ming-Ming Cheng1,Jufeng Yang1∗ 1College of Computer Science,Nankai University,Tianjin,China 2School of Computer Science and Informatics,Cardiff University,Cardiff,UKResearch Only

IP102

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 upperlevel category

Dataset Attributes

Label SVG
TasksClassification
Label SVG
CategoriesObject, Detection, Pest, Insect
Label SVG
SensorRGB Camera

Class Labels

rice leaf rollerrice leaf caterpillarpaddy stem maggotasiatic rice boreryellow rice borerrice gall midgeRice Stemflybrown plant hopperwhite backed plant hoppersmall brown plant hopper