Ushasi Chaudhuri

Ushasi Chaudhuri
University of Illinois, Urbana-Champaign | UIUC

Doctor of Philosophy

About

31
Publications
2,892
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
268
Citations
Citations since 2016
30 Research Items
268 Citations
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
Introduction
Ms. Chaudhuri is currently pursuing her Ph.D. in the retrieval of cross-sensor remote sensing images using artificial intelligence from the Indian Institute of Technology, Bombay. She obtained her master's degree from the Indian Institute of Technology, Kharagpur. Her current research interests include visual analysis, image processing, artificial intelligence, earth observation, and pattern recognition.
Additional affiliations
September 2019 - December 2019
Conservatoire National des Arts et Métiers
Position
  • Research expert
Description
  • Collaborated with Prof. Mihai Datcu (DLR) on inter-band retrieval and classification problems using BigEarthNet data archive from Sentinel-2 satellite.
January 2018 - present
Indian Institute of Technology Bombay
Position
  • Research Assistant
Description
  • Courses taken: CMInDS, Advanced Machine Learning, IIT Bombay. GNR 652, Machine Learning for Remote Sensing, IIT Bombay. GNR 792, Communication skills, IIT Bombay. GNR 638, Deep Learning for Image Analysis, IIT Bombay.
June 2015 - September 2017
Indian Institute of Technology Kharagpur
Position
  • Junior project officer
Description
  • Developed new methods to improve character recognition, spotting, and logo retrieval in document imaging using rough set theory on isothetic covers of characters.
Education
January 2018 - August 2021
Indian Institute of Technology Bombay
Field of study
  • Cross-Modal Data Retrieval for Remote Sensing Images using Deep Learning Techniques.
June 2015 - September 2017
Indian Institute of Technology Kharagpur
Field of study
  • Rough Set Based Analysis of Document Images
July 2011 - June 2015
University of Mumbai
Field of study
  • Electronics and telecommunication

Publications

Publications (31)
Article
The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges. The immense distributions-gap between the sketches and the images requires a proper domain alignment. Moreover, the fine-grained nature of the task and the high intra-class variance of many categories necessitates a class-wise discriminative mappi...
Preprint
The performance of a zero-shot sketch-based image retrieval (ZS-SBIR) task is primarily affected by two challenges. The substantial domain gap between image and sketch features needs to be bridged, while at the same time the side information has to be chosen tactfully. Existing literature has shown that varying the semantic side information greatly...
Preprint
Full-text available
The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges. The immense distributions-gap between the sketches and the images requires a proper domain alignment. Moreover, the fine-grained nature of the task and the high intra-class variance of many categories necessitates a class-wise discriminative mappi...
Article
The performance of a deep-learning-based model primarily relies on the diversity and size of the training dataset. However, obtaining such a large amount of labeled data for practical remote sensing (RS) applications is expensive and labor-intensive. Training protocols have been previously proposed for few-shot learning (FSL) and zero-shot learning...
Article
Full-text available
Conventional remote sensing data analysis techniques have a significant bottleneck of operating on a selectively chosen small-scale dataset. Availability of an enormous volume of data demands handling large-scale, diverse data, which have been made possible with neural network-based architectures. This work exploits the contextual information captu...
Data
This document is supplementary material to the manuscript, ``A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images'', which has been accepted in GRSL 2021. We provide additional experimental results and descriptions in this supplementary submission.
Article
Building footprints and road network detection have gained significant attention for map preparation, humanitarian aid dissemination, disaster management, to name a few. Traditionally, morphological filters excel at extracting shape features from remotely sensed images and have been widely used in the literature. However, the structural element (SE...
Article
Graph convolution networks (GCNs) are useful in remote sensing (RS) image retrieval. It is found to be effective because, in a graph representation, the relative geometrical interactions between different regions (or segments) are appropriately captured, along with their region-wise features in their region adjacency graphs. Also, the attention mec...
Article
Full-text available
Classification of crop types using Earth Observation (EO) data is a challenging task. The challenge increases many folds when we have diverse crops within a resolution cell. In this regard, optical and Synthetic Aperture Radar (SAR) data provide complementary information about the characteristics of a target. Therefore, we propose to leverage the s...
Conference Paper
In this work, we address a cross-modal retrieval problem in remote sensing (RS) data. A cross-modal retrieval problem is more challenging than the conventional uni-modal data retrieval frameworks as it requires learning of two completely different data representations to map onto a shared feature space. For this purpose, we chose a photo-sketch RS...
Preprint
Full-text available
We propose a novel framework for cross-modal zero-shot learning (ZSL) in the context of sketch-based image retrieval (SBIR). Conventionally, the SBIR schema mainly considers simultaneous mappings among the two image views and the semantic side information. Therefore, it is desirable to consider fine-grained classes mainly in the sketch domain using...
Preprint
Rough set is a well-studied subject with a theoretical foundation and many applications. However, its usage in image processing has been very sparse. Most of the well-known algorithms for document image processing related to character recognition, character spotting, and logo retrieval resort to supervised classification, causing the system to slow...
Article
Domain-agnostic data retrieval has lately become essential amidst the availability of large-scale data from different types of sensors. However, the unavailability of a sufficient amount of samples of certain classes during training curtails the utility of existing retrieval models in remote sensing (RS) applications. Here, we propose a novel frame...
Preprint
Full-text available
We deal with the problem of semantic classification of challenging and highly-cluttered dataset. We present a novel, and yet a very simple classification technique by leveraging the ease of classifiability of any existing well separable dataset for guidance. Since the guide dataset which may or may not have any semantic relationship with the experi...
Preprint
Full-text available
Conventional existing retrieval methods in remote sensing (RS) are often based on a uni-modal data retrieval framework. In this work, we propose a novel inter-modal triplet-based zero-shot retrieval scheme utilizing a sketch-based representation of RS data. The proposed scheme performs efficiently even when the sketch representations are marginally...
Article
We propose a novel framework for cross-modal zero-shot learning (ZSL) in the context of sketch-based image retrieval (SBIR). Conventionally, the SBIR schema mainly considers simultaneous mappings among the two image views and the semantic side information. Therefore, it is desirable to consider fine-grained classes mainly in the sketch domain using...
Article
Full-text available
In this study, we propose a sequence-to-sequence neural network architecture to jointly estimate the plant area index (PAI) and wet biomass of canola and soybean. The PAI and wet biomass have considerable importance for crop growth stage mapping and monitoring. RADARSAT-2 quad-pol data along with in situ measurements of canola and soybean obtained...
Conference Paper
We deal with the problem of zero-shot cross-modal image retrieval involving color and sketch images through a novel deep representation learning technique. The problem of a sketch to image retrieval and vice-versa is of practical importance, and a trained model in this respect is expected to generalize beyond the training classes, e.g., the zero-sh...
Article
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. T...
Article
We address the problem of multi-label scene classification from Very High Resolution (VHR) satellite remote sensing (RS) images in this paper by exploring the deep graph convolutional network (GCN). Since a given VHR RS scene contains several local features, the traditional single-label classification frameworks do not convey the true semantics of...
Preprint
Full-text available
Searching for similar logos in the registered logo database is a very important and tedious task at the trademark office. Speed and accuracy are two aspects that one must attend to while developing a system for retrieval of logos. In this paper, we propose a rough-set based method to quantify the structural information in a logo image that can be u...
Preprint
Full-text available
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 multi-spectral imagery, and ii) multi-label image retrieval between very high resolution (VHR) images and speech based label annotations....
Article
This paper deals with the problem of content-based image retrieval (CBIR)of very high resolution (VHR)remote sensing (RS)images using the notion of a novel Siamese graph convolution network (SGCN). The GCN model has recently gained popularity in learning representations for irregular domain data including graphs. In the same line, we argue the effe...
Thesis
Rough set is a well-studied subject with a theoretical foundation and many applications. However, its usage in image processing has been very sparse. Most of the well-known algorithms for document image processing related to character recognition, character spotting, and logo retrieval resort to supervised classification, causing the system to slow...
Conference Paper
Most of the well-known OCR engines, such as Google Tesseract, resort to a supervised classification, causing the system drooping in speed with increasing diversity in font style. Hence, with an aim to resolve the tediousness and pitfalls of training an OCR system, but without compromising with its efficiency, we introduce here a novel rough-set-the...
Conference Paper
Various initiatives have been taken all over the world to involve the citizens in the collection and reporting of data to make better and informed data-driven decisions. Our work shows how the geotagged images collected through the general population can be used to combat Malaria and Dengue by identifying and visualizing localities that contain pot...

Network

Cited By

Projects

Projects (4)
Project
Utilization of synthetic aperture radar for the derivation of new features which could be beneficial to monitor and classify different agricultural crops using simple learning algorithms. Therefore, these features will enrich the physics behind scattering from targets which will assist the algorithm to better classify them without introducing more complexity.