deepgaze - Computer Vision library for human-computer interaction

•    Python

---

Update 04/06/2017 Article "Head pose estimation in the wild using Convolutional Neural Networks and adaptive gradient methods" have been accepted for publication in Pattern Recogntion (Elsevier). The Deepgaze CNN head pose estimator module is based on this work. Update 22/03/2017 Fixed a bug in mask_analysis.py and almost completed a more robust version of the CNN head pose estimator.

convolutional-neural-networks motion-tracking color-detection face-detection skin-detection motion-detection head-pose-estimation human-computer-interaction histogram-comparison histogram-intersection cnn particle-filter saliency-map

stellargraph - StellarGraph - Machine Learning on Graphs

•    Python

---

StellarGraph is a Python library for machine learning on graphs and networks. StellarGraph is built on TensorFlow 2 and its Keras high-level API, as well as Pandas and NumPy. It is thus user-friendly, modular and extensible. It interoperates smoothly with code that builds on these, such as the standard Keras layers and scikit-learn, so it is easy to augment the core graph machine learning algorithms provided by StellarGraph. It is thus also easy to install with pip or Anaconda.

machine-learning graphs machine-learning-algorithms networkx graph-data graph-analysis graph-machine-learning link-prediction graph-convolutional-networks gcn saliency-map interpretability geometric-deep-learning graph-neural-networks heterogeneous-networks stellargraph-library

saliency - TensorFlow implementation for SmoothGrad, Grad-CAM, Guided backprop, Integrated Gradients and other saliency techniques

•    Jupyter

---

If the sign of the value given by the saliency mask is not important, then use VisualizeImageGrayscale, otherwise use VisualizeImageDiverging. See the SmoothGrad paper for more details on which visualization method to use. This example iPython notebook shows these techniques is a good starting place.

machine-learning deep-learning deep-neural-networks tensorflow convolutional-neural-networks saliency-map object-detection image-recognition

deep-viz-keras - Implementations of some popular Saliency Maps in Keras

•    Jupyter

---

Each of them is accompanied with the corresponding smoothgrad version [https://arxiv.org/abs/1706.03825], which improves on any baseline method by adding random noise. Courtesy of https://github.com/tensorflow/saliency and https://github.com/mbojarski/VisualBackProp.

keras deep-learning convolutional-neural-networks visualization gradient saliency-map machine-learning

gmr-saliency - GMR Saliency Map

•    Javascript

---

C++ implementation for paper "Saliency Detection via Graph-Based Manifold Ranking" by Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan and Ming-Hsuan Yang. To appear in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013), Portland, June, 2013. This implementation was written originally by Chuan Yang ycscience86@gmail.com (3-clause BSD license) and uses an also open source SLIC implementation written by Vilson Vieira/The Grid vilson@thegrid.io.

saliency saliency-map computer-vision slic

saliency-salgan-2017 - SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

•    Python

---

We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Find the extended pre-print version of our work on arXiv. The shorter extended abstract presented as spotlight in the CVPR 2017 Scene Understanding Workshop (SUNw) is available here.

deep-learning deeplearning saliency-map convolutional-neural-networks visual