M2Det : Highly Accurate Object Detection Model
This is an introduction to「M2Det」, a machine learning model that can be used with ailia SDK. You can easily use this model to create AI applications using ailia SDK as well as many other ready-to-use ailia MODELS.
Overview
M2Det is a highly accurate object detection model proposed in November 2018. It can detect bounding boxes of objects from the 80 categories in COCO.
Conventional object detection uses an image classification backbone (Mobilenet, VGG, ResNet, etc.) to compute bounding boxes. For example, in SSD, after extracting features with the image classification backbone, the bounding box is calculated by adding a similar backbone in the later stage.
The same was true for ReinaDet, which uses Feature Pyramids, and although it uses more hierarchical features than SSD, the backbone of object detection was based on image classification.
In M2Det, after extracting features with the image classification backbone, a specialized backbone is used for object detection to achieve higher accuracy.
This backbone specialized for object detection is called MLFPN (Multi-Level Feature Pyramid Network), which uses TUM (Thinned U-shape Module) in a hierarchical manner.
TUM has the following structure.
Performance of M2Det
M2Det performs better than YOLOv3 and RetinaDet.
VGG-16 and ResNet-101 are used as backbone for M2Det. VGG-16 is faster and ResNet-101 is more accurate.
Usage
The ailia SDK sample below allows you to use M2Det, with a VGG-16 based M2Det that takes 3x512x512 as input.
You can use the following command to perform object detection using M2Det on a web camera.
$ python3 m2det.py -v 0Related topics
ax Inc. has developed ailia SDK, which enables cross-platform, GPU-based rapid inference.
ax Inc. provides a wide range of services from consulting and model creation, to the development of AI-based applications and SDKs. Feel free to contact us for any inquiry.
