Lecture 5 - Object detection and segmentation in computer vision
Teacher: Colin DECOURT (ANITI)
Lecture video
View the recorded lecture here (this will only be available for approximately 6 weeks after the course)
Contents
- From classification to object detection
- Object detection/segmentation challenges (MS-COCO, Pascal VOC)
- Object detection:
- Region-based detector vs. single shot detector
- From R-CNN to Faster R-CNN
- YOLO: an overview
- Evaluation metrics in object detection/segmentation
- Object segmentation
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Mask R-CNN
Slides (available)
Lab (available)
Additional resources