You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Saliency system to model the behaviour of human eye gaze using deep learning. The model uses pre-trained VGG like backbone network and upsamples the high level features extracted from various intermediate layers using bilinear interpolation.
This repo shows a MATLAB implementation of score-CAM (Wang et al., CVPR workshop, 2020). This method is the first gradient-free CAM-based visualization method for explaining CNN decision.
Unofficial Pytorch implementation of the paper 'Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps' experiment on ImageNet-1K
SaRa (Saliency-Driven Object Ranking) is a saliency-driven ranking model that does not require any training and can efficiently rank the visual saliency of an image.
This notebook demonstrates a number of saliency mask techniques, augmented with the SmoothGrad technique, using the VGG16, AlexNet, InceptioNet, MobileNet convolutional neural network in TF2.