Small Dataset-Based Object Detection: How Much Data is Enough?

In this episode, we’ll debunk a popular myth about machines only learning from large amounts of data, and share a use case of applying ML with a small dataset. We’ll focus on the task of object detection to understand machine learning applications in the real world. The overview is based on the experience of MobiDev's ML Team experts.

The article on this topic is available at: https://mobidev.biz/blog/object-detection-small-datasets-use-cases-machine-learning

Subscribe to MobiDev on social media:
Facebook https://www.facebook.com/MobiDev.Corporation
Twitter https://twitter.com/MobiDev_

00:30 MobiDev, a software development company
00:55 Intro
01:20 Object Detection use
01:45 Machine Learning in Object Detection
02:53 Object Detection solution process

04:05 Case Study 

05:32 Phase 1. Image collecting
06:15 Image annotations for Object Detection
06:42 Phase 2. Faster R-CNN
07:45 One-stage detectors
08:43 Feature Pyramid Networks
09:05 Amount of data
10:15 Phase 3. Exploration of trained models performance
11:15 Conclusion