(R-CNN) Rich feature hierarchies for accurate object detection and semantic segmentation (Girshick, Donahue, Darrell & Malik, 2013)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (Chen, Papandreou, Kokkinos, Murphy, and Yuille, 2016)
Mask R-CNN (He, Gkioxari, Dollár & Girshick, 2017)
Fast R-CNN (Girshick, 2015)
Please read more about the object detection API here: (link)
Please also read through the guides at the bottom of this page: (link)
Please also read up on checkpoints and how they work (link)
Please go through this official tutorial from Tensorflow to practice using the Object Detection API
(RetinaNet)"Focal Loss for Dense Object Detection" By- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollar 2017
"Fully Convolutional Networks for Semantic Segmentation"(Long, Shelhamer & Darrell, 2014)
Divam Gupta's GitHub account containing a subsample of the CamVid dataset to create a smaller dataset.
Downloadable Tensorflow Detection Models from TensorFlow 2 Detection Model Zoo
There is one interesting link I have found comparing SGD and Adam. The author claims SGD is the best optimizer.
U-Net: Convolutional Networks for Biomedical Image Segmentation (Ronneberger, Fischer & Brox, 2015)
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (Selvaraju, Cogswell, Das, Vedantam,
Parikh & Batra, 2019)
For an optional, conceptual look at GradCAM, please see these videos from Deeplearning.AI’s “AI for Medical Treatment” course. Content including: Interpreting CNN models; Localization maps;Heat maps
(ZFNet) Visualizing and Understanding Convolutional Networks (Zeiler & Fergus, 2013)
zombies has been moved to new place： https://storage.googleapis.com/tensorflow-3-public/datasets/training-zombie.zip
https://storage.googleapis.com/tensorflow-3-public/datasets/zombie-walk-frames.zip \