This project aims to study the kind of representations learned by ConvNets at different layers.

Neural network visualization tool after an optional model compression with parameter pruning: (integrated) gradients, guided/visual backpropagation, activation maps for the cao model on the IndianPines dataset

implementation of Visualising Image Classification Models and Saliency Maps

Going deeper into Deep CNNs through visualization methods: Saliency maps, optimize a random input image and deep dreaming with Keras

Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".

A toolkit for efficent computation of saliency maps for explainable AI attribution. This tool was developed at Lawrence Livermore National Laboratory.

Salient Object Detection in the Deep Learning Era: An In-Depth Survey

Awesome Explainable AI (XAI) and Interpretable ML Papers and Resources

Visualizer for PyTorch image models

Official Repository for ECCV 2020 paper "AiR: Attention with Reasoning Capability"

Programming assignments to demonstrate the Applications of Data Science. These were completed as part of the Plaksha Tech Leaders Fellowship program.

Explainability and Robustness in Metric Space

Codes for the AAAI 2021 paper "Locate Globally, Segment locally: A Progressive Architecture With Knowledge Review Network for Salient Object Detection"

PVCFA: Principal Variation Context Feature Attribution - Distributed Chess for Perturbation-based Saliency Maps

The official PyTorch implementation of IEEE Transactions on Image Processing 2021 paper "Rethinking the U-shape Structure for Salient Object Detection"

Official [WACV] Code Repository for "Saliency Guided Experience Packing for Replay in Continual Learning"

Visual Search Model: A Bayesian model for visual search on natural scenes.

This project uses Deep Learning to extract Salient text from an image using State-of-the-Art Vision Transformer Architecture.