Abstract: Object localization/detection is one of the most crucial tasks in artificial intelligence and computer vision. The importance of object detection is that most of the vision tasks start with object localization. Real-world applications such as autonomous driving, personal/industrial robotics, person counting, object tracking, surveillance, OCR (optical character recognition) need to localize the object in the given image or video.
Object detection has a long history. The researchers have been continuously working on improving object detection techniques. Before the deep learning era, hand-crafted features — haar-like features, HOGs (histogram of gradients), and deformable part models — were used to train an object localization classifier. With the great success of deep learning in computer vision, novel deep learning-based object detection methods (features extracted from deep convolutional neural networks) have been proposed. There are various very robust and high performing object detection methods which help to boost real-world applications.
In this tutorial, we will go through:
- the history of object detection — pre-deep learning methods object detection evaluation — evaluation metrics;
- benchmark datasets used for evaluation;
- cascade face detection methods (MTCNN);
- convolutional neural networks;
- the recent (deep learning-based) detection methods such as RCNN (Region Convolutional Neural Networks), Fast RCNN, Faster RCNN, RetinaNet, YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector);
- two-stage detectors vs. single-stage detectors;
- end-to-end object detection pipeline;
- practical tips and tricks in training object detection models.
Then, we will be discussing future research topics, and we will be asking and trying to answer some questions:
- How could the current object localization/detection methods be improved?
- What are the missing points in state-of-the-art object detection methods and datasets?
- What we should pay attention to have explainable and reliable detectors
- Which evaluation metrics we need to consider to be able to assess the detection methods in the right way?
Learning outcomes and takeaways:
- Learn about object detection history and the current status briefly,
- Evaluation metrics and their importance for real world applications,
- Practical tips for training object detection models,
- Get an idea about the future direction of object detection.
We are looking forward to seeing you in this tutorial and help us to rethink object detection!
- google colab (sign in with the google account)
- any deep learning framework (TensorFlow/Keras/PyTorch)
- basic computer vision knowledge
- convolutional neural network
Bio: Alisher Abdulkhaev is a Machine Learning Engineer working for Browzzin — AI powered Social Fashion App. Alisher is the co-director and board member at Machine Learning Tokyo—award winning non profit organization dedicated to democratizing machine learning.
Teaching Fellow, Board Director | Tokyo Data Science, Machine Learning Tokyo