Convolutional Neural Networks. Andrew Ng.
Convolutional Neural Networks. Part 3.
Part 3.
Object Detection. Convolutional Neural Networks.
¶Object localization
¶Landmark detection
¶Object detection
¶Convolutional implementation of sliding windows
¶Bounding box predictions
¶Intersection over union
¶Non-max suppression
¶Anchor boxes
¶Putting it together: YOLO algorithm
¶Region proposals (Optional)
¶Semantic segmentation with U-Net
¶Transpose Convolutions
¶U-Net Architecture intuition
¶U-Net Architecture
¶Papers
[Sermanet et al., 2014, OverFeat: Integrated recognition, localization and detection using convolutional networks]
[Redmon et al., 2015, You Only Look Once: Unified real-time object detection]
[Girshik et al., 2013, Rich feature hierarchies for accurate object detection and semantic segmentation]
[Girshik, 2015. Fast R-CNN]
[Ren et al., 2016. Faster R-CNN: Towards real-time object detection with region proposal networks]
[Novikov et al., 2017, Fully Convolutional Architectures for Multi-Class Segmentation in Chest Radiograghs]
[Dong et al., 2017, Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks]
[Ronneberger et al., 2015, U-Net: Convolutional Networks for Biomedical Image Segmentation]
