Time

TBA

Room

TBA

Organizers

• Ted Kuo
• Jenq-Neng Hwang
• Jiun-In Guo
• Marvin Chen
• Hsien-Kai Kuo
• Chia-Chi Tsai

Website

https://aidea-web.tw/icme2022

Description

Object detection in the computer vision area has been extensively studied and making tremendous progress in recent years. Furthermore, image segmentation takes it to a new level by trying to find out accurately the exact boundary of the objects in the image. Semantic segmentation is in pursuit of more than just location of an object, going down to pixel level information. However, due to the heavy computation required in most deep learning-based algorithms, it is hard to run these models on embedded systems, which have limited computing capabilities. In addition, the existing open datasets for traffic scenes applied in ADAS applications usually include main lane, adjacent lanes, different lane marks (i.e. double line, single line, and dashed line) in western countries, which is not quite similar to that in Asian countries like Taiwan with lots of motorcycle riders speeding on city roads, such that the semantic segmentation models training by only using the existing open datasets will require extra technique for segmenting complex scenes in Asian countries.

In this competition, we encourage the participants to design semantic segmentation model that can be applied in Taiwan’s traffic scene with lots of fast speeding motorcycles running on city roads along with vehicles and pedestrians. The developed models not only fit for embedded systems but also achieve high accuracy at the same time.

This competition includes two stages: qualification and final competition.

• Qualification competition: all participants submit their answers online. A score is calculated. The top 15 teams would be qualified to enter the final round of the competition.
• Final competition: the final score will be evaluated on new MediaTek platform (Dimensity Series) platform for the final score.

The goal is to design a lightweight deep learning semantic segmentation model suitable for constrained embedded system design to deal with traffic scenes in Asian countries like Taiwan. We focus on segmentation accuracy, power consumption, real-time performance optimization and the deployment on MediaTek’s Dimensity Series platform.

With MediaTek’s Dimensity Series platform and its heterogeneous computing capabilities such as CPUs, GPUs and APUs (AI processing units) embedded into the system-on-chip products, developers are provided the high performance and power efficiency for building the AI features and applications. Developers can target these specific processing units within the system-on-chip or, they can also let MediaTek NeuroPilot SDK intelligently handle the processing allocation for them.

Given the test image dataset, participants are asked to segment each pixel belonging to the following six classes {background, main_lane, alter_lane, double_line, dashed_line, single_line} in each image.

Time

TBA

Room

TBA

Organizers

• Hui Xue, Alibaba Group, China
• Dong Li, Alibaba Group, China
• Weigao Wen, Alibaba Group, China
• Yuan He, Alibaba Group, China
• Xuan Jin, Alibaba Group, China
• Jianmin Pan, Alibaba Group, China
• Hang Su, Tsinghua University, China

Website

https://tianchi.aliyun.com/competition/entrance/531948/introduction?lang=en-us

Description

In e-commerce, logo detection of products can provide protection of the entrepreneurs’ and business owners’ hard-earned creations and ideas from malign usage and plagiarism. We propose the grand challenge of few-shot logo detection, which is a task that requires a model to detect logos by handling tiny logo instances, similar brands, and adversarial images at the same time, with limited annotations.

This challenge aims to exchange ideas and discuss the problem for both academic and industrial researchers, and to seek a few-shot logo detection framework. We would like to characterize the properties that empower few-shot detection models, and to shed light on future directions for cross-community collaborations.