MSI Net ======= 📖 Contextual encoder decoder network for visual saliency prediction 🤗 A demo of this model can be found on HuggingFace Spaces. Summary MSI Net is a visual saliency model that predicts where humans fixate on natural images using a contextual encoder decoder network trained on eye movement data. The model is based on a convolutional neural network architecture and includes an ASPP module with multiple convolutional layers at different dilation rates to capture multi scale features in parallel. Moreover, it combines the resulting representations with global scene information towards accurate predictions of visual saliency. MSI Net consists of roughly 25M parameters and thus presents a suitable choice for applications with limited computational resources. For more information on the model, check out GitHub and the corresponding paper or preprint. Requirements To install the required dependencies, use either pip or conda : Example Use Import the dependencies Download the repo files Load the saliency model Load the functions for preprocessing the input and postprocessing the output Load and preprocess an example image Feed the input tensor to the model Postprocess and v…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy