Ushasi Chaudhuri's Projects
We deal with the problem of zero-shot cross-modal image retrieval involving color and sketch images through a novel deep representation learning technique.
Neural Network from scratch Using CUDA
🛰️ List of satellite image training datasets with annotations for computer vision and deep learning
Implementation of Canny edge detector
Using sklearn, in Python. Implementation includes Random forest and XGBoost classifier.
We address the problem of cross-modal information retrieval in the domain of remote sensing. In particular, we are interested in two application scenarios: i) cross-modal retrieval between panchromatic (PAN) and multispectral imagery, and ii) multi-label image retrieval between very high resolution (VHR) images and speech-based label annotations. These multi-modal retrieval scenarios are more challenging than the traditional uni-modal retrieval approaches given the inherent differences in distributions between the modalities. However, with the increasing availability of multi-source remote sensing data and the scarcity of enough semantic annotations, the task of multi-modal retrieval has recently become extremely important. In this regard, we propose a novel deep neural network-based architecture that is considered to learn a discriminative shared feature space for all the input modalities, suitable for semantically coherent information retrieval. Extensive experiments are carried out on the benchmark large-scale PAN - multispectral DSRSID dataset and the multi-label UC-Merced dataset. Together with the Merced dataset, we generate a corpus of speech signals corresponding to the labels. Superior performance with respect to the current state-of-the-art is observed in all the cases.
Context-attended Graph Convolution Network for Remote Sensing Images
Doodle to Search: Practical Zero Shot Sketch Based Image Retrieval
Sketch-based aerial image retrieval
In this example, we use the pre-trained ResNet50 model, which is pretrained on the ImageNet dataset. The implementation is in TensorFlow-Keras.
How to Learn More? Exploring the Possibility of Kolmogorov-Arnold Networks for Hyperspectral Image Classification
Convertion of an RGB image to a Region Adjacency Graph (RAG) using SLIC super-pixel based segmentation technique.
Isothetic covers and convex hull for character recognition
Code repository for the C-MInDS, IIT Bombay course.
Implementation of Multi-View Information Bottleneck
Graph Convolutional Networks in PyTorch
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
A list of radar and optical satellite datasets for detection, classification, semantic segmentation and instance segmentation tasks.
A list of radar and optical satellite datasets for ship detection, classification, semantic segmentation and instance segmentation tasks.
Siamese graph convolutional network for content based remote sensing image retrieval
A SimCLR implementation for self-supervised learning from unlabeled data
Essential codes for result analysis