1st International Workshop on

Generalizing from Limited Resources in the Open World

IJCAI 2023 Workshop | Macao, S.A.R | August 20, 2023

Challenge

Based on our published X-ray open-world prohibited item detection datasets, we also bring a challenge to encourage participants use sparse training data to design models which are capable to effectively identify known and unknown prohibited objects, and promote the protection of public transport safety in society. This challenge devise two different tracks for participators, namely horizontal object detection and rotated object detection for X-ray prohibited items according to practical demand. Welcome to join the challenge at our platform!

Track 1：Horizontal Detection

Security inspectors struggle to accurately detect the prohibited items in daily security inspection, which may cause severe danger to the public. Therefore, it is vital to develop a rapid, accurate and automatic detection model using powerful deep learning method.

To accelerate the research on enhancing horizontal object detection performance in the X-ray scenario, we organize this challenge track, where image data in real X-ray security inspection scene with horizontal bounding boxes are provided .

Track 2：Rotated Detection

Horizontal bounding boxes are incapable of representing slender prohibited items in various orientations, which involve in massive background information. Therefore exploring rotated object detection task on X-ray security inspection scenario is significant.

To accelerate the research on enhancing rotated object detection performance in the X-ray scenario, we organize this challenge track, where image data in real X-ray security inspection scene with rotated bounding boxes are provided .

Timeline

Price

Award List

Free GPU Hours !

OpenI Community ( https://git.openi.org.cn ) is an open-source platform and community organized by AITISA ( http://www.aitisa.org.cn/ ), that provides code hosting, collaborative development, online debugging, model training and is shared by industry-university-research cooperation. Inclusive computing resources (including NVIDIA GPUs and Ascend NPU processors) are currently available to all challenge participants. Join our group chat for more details.