not fully observed, scale distraction, illumination changes.
bounding box and class labels,
intersection of union (IoU)
See more at: Evaluationg Mateics
feature extractor, computationally expensive, lower widthe and height, greater depth
Prior bounding boxes, or anchor bounding boxes, assume bounding boxes, then guess where and how large they are.
centroid location (where), box dimensions (size)
Non-maximum suppression, nms, remove anchor boxes.
minibatch selection for boxes during training is important
hard negative anchor mining, control training bias
Loss functions, for classificatoin we have cross entropy, for regression we have
- Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2), 303-338.
- Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91-99).
- Redmon, Joseph, et al. “You only look once: Unified, real-time object detection.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
- (Optional) Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016, October). SSD: Single shot multibox detector. In European conference on computer vision.