As part of the Explainable AI Toolkit (XAITK), XAITK-Saliency is an open source, explainable AI framework for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications.
-
Updated
May 23, 2024 - Python
As part of the Explainable AI Toolkit (XAITK), XAITK-Saliency is an open source, explainable AI framework for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications.
C++ code for "Single object tracking using particle filter framework and saliency-based weighted color histogram"
PySODMetrics: A Simple and Efficient Implementation of Grayscale/Binary Segmentation Metrcis
PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection
Code for SCOUT (Task- and Context Modulated Attention for driving) and extended annotations for DR(eye)VE, BDD-A, and LBW datasets
mask-to-annotation is a powerful and efficient tool for automatically generating annotations in popular computer vision formats such as COCO, YOLO, and VGG from binary masks.
Modeling the impact of various pathological states on early primate visual attention mechanisms
Pytorch Implementation of the Explainable Conditional Adversarial Autoencoder using Saliency Maps and SHAP (J. of Imaging - MDPI)
Content-Based Radiogrphic Image Retrieval with Deep Learning and Interpretability of Results using Saliency and Grad-CAM
Neural network visualization toolkit for tf.keras
Predict areas of high visual importance
mask-to-annotation is a powerful and efficient tool for automatically generating annotations in popular computer vision formats such as COCO, YOLO, and VGG from saliency masks.
Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).
Code for metrics used in the I. Kotseruba et al. "Do Saliency Models Detect Odd-One-Out Targets?" paper
This research is based on efficient saliency detection using deformable convolutions.
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.
A suite of tests to assess attention faithfulness for explainability
Unified Image and Video Saliency Modeling (ECCV 2020)
UGC Quality Assessment: Exploring the Impact of Saliency in Deep Feature-Based Quality Assessment
[ICCV 23] Official implementation of Source-free Depth for Object Pop-out (One of First Attempts for RGB-D COD)
Add a description, image, and links to the saliency topic page so that developers can more easily learn about it.
To associate your repository with the saliency topic, visit your repo's landing page and select "manage topics."