Hrishikesh Sharma
Research Subjects
Hrishikesh Sharma has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Ayush Bachan
TCS Research
2 shared publications - Binuja Varma
TCS Genomics Lab, Tata Consultancy Services Limited, Noida, Uttar Pradesh, India 201313
2 shared publications - Geetashree Mukherjee
Tata Medical Center, Kolkata, India
2 shared publications - Naveen Sivadasan
Tata Consultancy Services Ltd
2 shared publications - Riya Sadrani
TCS Research
2 shared publications - Sujatha Kotte
Tata Consultancy Services Ltd
2 shared publications
Latest Publications
- 12 May 2025
- Published by Springer Nature
- p. 244-258
On The Relationship Between Visual Anomaly-Free and Anomalous Representations
- 12 May 2025
- Published by Springer Nature
- p. 244-258
On The Relationship Between Visual Anomaly-Free and Anomalous Representations
- Open Access
On The Relationship between Visual Anomaly-free and Anomalous Representations
Anomaly Detection is an important problem within computer vision, having variety of real-life applications. Yet, the current set of solutions to this problem entail known, systematic shortcomings. Specifically, contemporary surface Anomaly Detection task assumes the presence of multiple specific anomaly classes e.g. cracks, rusting etc., unlike one-class classification model of past. However, building a deep learning model in such setup remains a challenge because anomalies arise rarely, and hence anomaly samples are quite scarce. Transfer learning has been a preferred paradigm in such situations. But the typical source domains with large dataset sizes e.g. ImageNet, JFT-300M, LAION-2B do not correlate well with the domain of surfaces and materials, an important premise of transfer learning. In this paper, we make an important hypothesis and show, by exhaustive experimentation, that the space of anomaly-free visual patterns of the normal samples correlates well with each of the various spaces of anomalous patterns of the class-specific anomaly samples. The first results of using this hypothesis in transfer learning have indeed been quite encouraging. We expect that finding such a simple closeby domain that readily entails large number of samples, and which also oftentimes shows interclass separability though with narrow margins, will be a useful discovery. Especially, it is expected to improve domain adaptation for anomaly detection, and few-shot learning for anomaly detection, making in-the-wild anomaly detection realistically possible in future.
Open AccessOn The Relationship between Visual Anomaly-free and Anomalous Representations
Anomaly Detection is an important problem within computer vision, having variety of real-life applications. Yet, the current set of solutions to this problem entail known, systematic shortcomings. Specifically, contemporary surface Anomaly Detection task assumes the presence of multiple specific anomaly classes e.g. cracks, rusting etc., unlike one-class classification model of past. However, building a deep learning model in such setup remains a challenge because anomalies arise rarely, and hence anomaly samples are quite scarce. Transfer learning has been a preferred paradigm in such situations. But the typical source domains with large dataset sizes e.g. ImageNet, JFT-300M, LAION-2B do not correlate well with the domain of surfaces and materials, an important premise of transfer learning. In this paper, we make an important hypothesis and show, by exhaustive experimentation, that the space of anomaly-free visual patterns of the normal samples correlates well with each of the various spaces of anomalous patterns of the class-specific anomaly samples. The first results of using this hypothesis in transfer learning have indeed been quite encouraging. We expect that finding such a simple closeby domain that readily entails large number of samples, and which also oftentimes shows interclass separability though with narrow margins, will be a useful discovery. Especially, it is expected to improve domain adaptation for anomaly detection, and few-shot learning for anomaly detection, making in-the-wild anomaly detection realistically possible in future.
- Open Access
A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision
Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application of GAN models, which are notoriously hard to train, but produce good results if trained well. There have been many a surveys on GANs, organizing the vast GAN literature from various focus and perspectives. However, none of the surveys brings out the important chronological aspect: how the multiple challenges of employing GAN models were solved one-by-one over time, across multiple landmark research works. This survey intends to bridge that gap and present some of the landmark research works on the theory and application of GANs, in chronological order.
Open AccessA Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision
Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application of GAN models, which are notoriously hard to train, but produce good results if trained well. There have been many a surveys on GANs, organizing the vast GAN literature from various focus and perspectives. However, none of the surveys brings out the important chronological aspect: how the multiple challenges of employing GAN models were solved one-by-one over time, across multiple landmark research works. This survey intends to bridge that gap and present some of the landmark research works on the theory and application of GANs, in chronological order.
- Open Access
- 25 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Supervised Vision-based Anomaly Detection
- 25 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessSupervised Vision-based Anomaly Detection
- 30 May 2023
- Published by Springer Nature
- p. 221-225
A Deep Learning Based Ensemble Model for Generalized Mitosis Detection in H &E Stained Whole Slide Images
- 30 May 2023
- Published by Springer Nature
- p. 221-225
A Deep Learning Based Ensemble Model for Generalized Mitosis Detection in H &E Stained Whole Slide Images
- Open Access
A Robust Deep Learning Approach for Joint Nuclei Detection and Cell Classification in Pan-Cancer Histology Images
Advanced image processing methods have shown promise in computational pathology, including the extraction of crucial microscopic features from histology images. Accurate detection and classification of cell nuclei from whole-slide images (WSI) play a crucial role in capturing the molecular and morphological landscape of the tissue sample. They enable widespread downstream applications, including cancer diagnosis, prognosis, and discovery of novel markers. Robust nuclei detection and classification are challenging due to the high intra-class variability and inter-class similarity of the microscopic morphological features. This is further compounded by the domain shift arising due to the variability in tissue types, staining protocols, and image acquisition. Motivated by the ability of the recent deep learning techniques to learn complex patterns in a biasfree manner, we develop a novel and robust deep learning model TransNuc, based on vision transformers, for simultaneous detection and classification of cell nuclei from H&E stained WSI. We benchmarked TransNuc on the comprehensive Open Pan-cancer Histology Dataset (PanNuke), sampled from over 20,000 WSI, comprising 19 different tissue types and five clinically important cell classes, namely, Neoplastic, Epithelial, Inflammatory, Connective, and Dead cells. TransNuc exhibited superior performance compared to the state-of-theart, including Hover-Net and Micro-Net. TransNuc was able to learn robust feature representations and thereby perform consistently better for the abundant classes such as neoplastic, and the under-represented classes such as dead cells. Similar performance gains were also obtained for epithelial and connective classes that have a significant inter-class morphological similarity.
Open AccessA Robust Deep Learning Approach for Joint Nuclei Detection and Cell Classification in Pan-Cancer Histology Images
Advanced image processing methods have shown promise in computational pathology, including the extraction of crucial microscopic features from histology images. Accurate detection and classification of cell nuclei from whole-slide images (WSI) play a crucial role in capturing the molecular and morphological landscape of the tissue sample. They enable widespread downstream applications, including cancer diagnosis, prognosis, and discovery of novel markers. Robust nuclei detection and classification are challenging due to the high intra-class variability and inter-class similarity of the microscopic morphological features. This is further compounded by the domain shift arising due to the variability in tissue types, staining protocols, and image acquisition. Motivated by the ability of the recent deep learning techniques to learn complex patterns in a biasfree manner, we develop a novel and robust deep learning model TransNuc, based on vision transformers, for simultaneous detection and classification of cell nuclei from H&E stained WSI. We benchmarked TransNuc on the comprehensive Open Pan-cancer Histology Dataset (PanNuke), sampled from over 20,000 WSI, comprising 19 different tissue types and five clinically important cell classes, namely, Neoplastic, Epithelial, Inflammatory, Connective, and Dead cells. TransNuc exhibited superior performance compared to the state-of-theart, including Hover-Net and Micro-Net. TransNuc was able to learn robust feature representations and thereby perform consistently better for the abundant classes such as neoplastic, and the under-represented classes such as dead cells. Similar performance gains were also obtained for epithelial and connective classes that have a significant inter-class morphological similarity.
- Open Access
A Quantum-Classical Hybrid Method for Image Classification and Segmentation
Enormous activity in the Quantum Computing area has resulted in considering them to solve different difficult problems, including those of applied nature, together with classical computers. An attempt is made in this work to nail down a pipeline consisting of both quantum and classical processing blocks for the task of image classification and segmentation in a systematic fashion. Its efficacy and utility are brought out by applying it to Surface Crack segmentation. Being a sophisticated software engineering task, the functionalities are orchestrated through our in-house Cognitive Model Management framework.
Open AccessA Quantum-Classical Hybrid Method for Image Classification and Segmentation
Enormous activity in the Quantum Computing area has resulted in considering them to solve different difficult problems, including those of applied nature, together with classical computers. An attempt is made in this work to nail down a pipeline consisting of both quantum and classical processing blocks for the task of image classification and segmentation in a systematic fashion. Its efficacy and utility are brought out by applying it to Surface Crack segmentation. Being a sophisticated software engineering task, the functionalities are orchestrated through our in-house Cognitive Model Management framework.
- 2 June 2017
- Published by Springer Nature
- p. 586-595
A Lattice-Theoretic Approach for Segmentation of Truss-Like Porous Objects in Outdoor Aerial Scenes
- 2 June 2017
- Published by Springer Nature
- p. 586-595
A Lattice-Theoretic Approach for Segmentation of Truss-Like Porous Objects in Outdoor Aerial Scenes
- 4 July 2015
- Published by Springer Nature
- p. 71-81
A Real-Time Framework for Detection of Long Linear Infrastructural Objects in Aerial Imagery
- 4 July 2015
- Published by Springer Nature
- p. 71-81
A Real-Time Framework for Detection of Long Linear Infrastructural Objects in Aerial Imagery
- 9 June 2015
- Published by Springer Nature
- p. 641-651
Image Analysis-Based Automatic Detection of Transmission Towers using Aerial Imagery
- 9 June 2015
- Published by Springer Nature
- p. 641-651
Image Analysis-Based Automatic Detection of Transmission Towers using Aerial Imagery