Search

Surveillance and surveying are two important applications of empirical research. A major part of terrain modelling is supported by photographic surveys which are used for capturing expansive natural surfaces using a wide range of sensors -- visual, infrared, ultrasonic, radio, etc. A natural surface is non-smooth, unpredictable and fast-varying, and it is difficult to capture all features and reconstruct them accurately. An orthographic image of a surface provides a detailed holistic view capturing its relevant features. In a perfect orthographic reconstruction, images must be captured normal to each point on the surface which is practically impossible. In this paper, a detailed analysis of the constraints on imaging distance is also provided. A novel method is formulated to determine an approximate orthographic region on a surface surrounding the point of focus and additionally, some methods for approximating the orthographic boundary for faster computation is also proposed. The approximation methods have been compared in terms of computational efficiency and accuracy., Comment: arXiv admin note: substantial text overlap with arXiv:2305.08121

Adaptation of a classifier to new domains is one of the challenging problems in machine learning. This has been addressed using many deep and non-deep learning based methods. Among the methodologies used, that of adversarial learning is widely applied to solve many deep learning problems along with domain adaptation. These methods are based on a discriminator that ensures source and target distributions are close. However, here we suggest that rather than using a point estimate obtaining by a single discriminator, it would be useful if a distribution based on ensembles of discriminators could be used to bridge this gap. This could be achieved using multiple classifiers or using traditional ensemble methods. In contrast, we suggest that a Monte Carlo dropout based ensemble discriminator could suffice to obtain the distribution based discriminator. Specifically, we propose a curriculum based dropout discriminator that gradually increases the variance of the sample based distribution and the corresponding reverse gradients are used to align the source and target feature representations. An ensemble of discriminators helps the model to learn the data distribution efficiently. It also provides a better gradient estimates to train the feature extractor. The detailed results and thorough ablation analysis show that our model outperforms state-of-the-art results., Comment: This work is an extension of our BMVC-2019 paper (arXiv:1907.10628)

Public feeding programs continue to be a major source of nutrition to a large part of the population across the world. Any disruption to these activities, like the one during the Covid-19 pandemic, can lead to adverse health outcomes, especially among children. Policymakers and other stakeholders must balance the need for continuing the feeding programs while ensuring the health and safety of workers engaged in the operations. This has led to several innovations that leverage advanced technologies like AI and IOT to monitor the health and safety of workers and ensure hygienic operations. However, there are practical challenges in its implementation on a large scale. This paper presents an implementation framework to build resilient public feeding programs using a combination of intelligent technologies. The framework is a result of piloting the technology solution at a facility run as part of a large mid-day meal feeding program in India. Using existing resources like CCTV cameras and new technologies like AI and IOT, hygiene and safety compliance anomalies can be detected and reported in a resource-efficient manner. It will guide stakeholders running public feeding programs as they seek to restart suspended operations and build systems that better adapt to future crises., Comment: 4 pages, 3 figures. To appear ICSE Workshop on Software Engineering for Healthcare, June 3, 2021, virtual

Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availability of actual source samples is not always possible in practical cases. It could be due to memory constraints, privacy concerns, and challenges in sharing data. This practical scenario creates a bottleneck in the domain adaptation problem. This paper addresses this challenging scenario by proposing a domain adaptation technique that does not need any source data. Instead of the source data, we are only provided with a classifier that is trained on the source data. Our proposed approach is based on a generative framework, where the trained classifier is used for generating samples from the source classes. We learn the joint distribution of data by using the energy-based modeling of the trained classifier. At the same time, a new classifier is also adapted for the target domain. We perform various ablation analysis under different experimental setups and demonstrate that the proposed approach achieves better results than the baseline models in this extremely novel scenario., Comment: Published- WACV-2021

One of the major limitations of deep learning models is that they face catastrophic forgetting in an incremental learning scenario. There have been several approaches proposed to tackle the problem of incremental learning. Most of these methods are based on knowledge distillation and do not adequately utilize the information provided by older task models, such as uncertainty estimation in predictions. The predictive uncertainty provides the distributional information can be applied to mitigate catastrophic forgetting in a deep learning framework. In the proposed work, we consider a Bayesian formulation to obtain the data and model uncertainties. We also incorporate self-attention framework to address the incremental learning problem. We define distillation losses in terms of aleatoric uncertainty and self-attention. In the proposed work, we investigate different ablation analyses on these losses. Furthermore, we are able to obtain better results in terms of accuracy on standard benchmarks., Comment: Accepted WACV 2021

Domain adaptation is essential to enable wide usage of deep learning based networks trained using large labeled datasets. Adversarial learning based techniques have shown their utility towards solving this problem using a discriminator that ensures source and target distributions are close. However, here we suggest that rather than using a point estimate, it would be useful if a distribution based discriminator could be used to bridge this gap. This could be achieved using multiple classifiers or using traditional ensemble methods. In contrast, we suggest that a Monte Carlo dropout based ensemble discriminator could suffice to obtain the distribution based discriminator. Specifically, we propose a curriculum based dropout discriminator that gradually increases the variance of the sample based distribution and the corresponding reverse gradients are used to align the source and target feature representations. The detailed results and thorough ablation analysis show that our model outperforms state-of-the-art results., Comment: BMVC 2019 Accepted, Project Page: https://delta-lab-iitk.github.io/CD3A/