ushasi

A-Simplified-framework-for-Zero-shot-Cross-Modal-Sketch-Data-Retrieval

We deal with the problem of zero-shot cross-modal image retrieval involving color and sketch images through a novel deep representation learning technique.

Canny-Edge-Detector

Implementation of Canny edge detector

CMIR-NET-A-deep-learning-based-model-for-cross-modal-retrieval-in-remote-sensing

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.

Earth-on-Canvas-dataset

Sketch-based aerial image retrieval

Fine-tuning-and-feature-extraction-from-pretrained-models

In this example, we use the pre-trained ResNet50 model, which is pretrained on the ImageNet dataset. The implementation is in TensorFlow-Keras.

Image-to-Region-Adjacency-Graph-creation

Convertion of an RGB image to a Region Adjacency Graph (RAG) using SLIC super-pixel based segmentation technique.

MachineLearning

Code repository for the C-MInDS, IIT Bombay course.

multi-label-analysis

Siamese-spatial-Graph-Convolution-Network

Siamese graph convolutional network for content based remote sensing image retrieval

simCLR

A SimCLR implementation for self-supervised learning from unlabeled data

ushasi/A-Simplified-framework-for-Zero-shot-Cross-Modal-Sketch-Data-Retrieval

We deal with the problem of zero-shot cross-modal image retrieval involving color and sketch images through a novel deep representation learning technique.

ushasi/Image-to-Region-Adjacency-Graph-creation

Convertion of an RGB image to a Region Adjacency Graph (RAG) using SLIC super-pixel based segmentation technique.

ushasi/Siamese-spatial-Graph-Convolution-Network

Siamese graph convolutional network for content based remote sensing image retrieval

ushasi/CMIR-NET-A-deep-learning-based-model-for-cross-modal-retrieval-in-remote-sensing

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.

ushasi/MachineLearning

Code repository for the C-MInDS, IIT Bombay course.

ushasi/Earth-on-Canvas-dataset

Sketch-based aerial image retrieval

ushasi/multi-label-analysis

ushasi/Canny-Edge-Detector

Implementation of Canny edge detector

ushasi/Fine-tuning-and-feature-extraction-from-pretrained-models

In this example, we use the pre-trained ResNet50 model, which is pretrained on the ImageNet dataset. The implementation is in TensorFlow-Keras.

ushasi/Remote-Sensing-Datasets

A list of radar and optical satellite datasets for detection, classification, semantic segmentation and instance segmentation tasks.

ushasi/ANN_gpu

Neural Network from scratch Using CUDA

ushasi/simCLR

A SimCLR implementation for self-supervised learning from unlabeled data

ushasi/awesome-satellite-imagery-datasets

🛰️ List of satellite image training datasets with annotations for computer vision and deep learning

ushasi/Context-attended-Graph-Convolution-Network

Context-attended Graph Convolution Network for Remote Sensing Images

ushasi/CrossATNet-A-Novel-Cross-Attention-Based-Frameworkfor-Sketch-Based-Image-Retrieval

ushasi/doodle2search

Doodle to Search: Practical Zero Shot Sketch Based Image Retrieval

ushasi/Dual-Path-Morph-UNet

ushasi/Dummy_images

ushasi/HSIConvKAN

How to Learn More? Exploring the Possibility of Kolmogorov-Arnold Networks for Hyperspectral Image Classification

ushasi/Isothetic-covers

Isothetic covers and convex hull for character recognition

ushasi/Logo-segmentation

ushasi/Multi-View-Information-Bottleneck

Implementation of Multi-View Information Bottleneck

ushasi/Presentations

ushasi/pygcn

Graph Convolutional Networks in PyTorch

ushasi/PyTorch-BayesianCNN

Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.

ushasi/Satellite-Imagery-Datasets-Containing-Ships

A list of radar and optical satellite datasets for ship detection, classification, semantic segmentation and instance segmentation tasks.

ushasi/Ship-Detection-Challenge

ushasi/tSNE-plot-and-Bar-graphs

Essential codes for result analysis

ushasi/UCMerced-speech-audio-samples

ushasi/ushasi