Abstract

Many populous countries including India areburdened with a considerable backlog of legalcases. Development of automated systems thatcould process legal documents and augmentlegal practitioners can mitigate this. However,there is a dearth of high-quality corpora that isneeded to develop such data-driven systems.The problem gets even more pronounced inthe case of low resource languages such asHindi. In this resource paper, we introducetheHindi Legal Documents Corpus (HLDC), acorpus of more than 900K legal documents inHindi. Documents are cleaned and structuredto enable the development of downstream ap-plications. Further, as a use-case for the cor-pus, we introduce the task of bail prediction.We experiment with a battery of models andpropose a Multi-Task Learning (MTL) basedmodel for the same. MTL models use sum-marization as an auxiliary task along with bailprediction as the main task. Experiments withdifferent models are indicative of the needfor further research in this area. We releasethe corpus and model implementation codewith this paper:https://github.com/Exploration-Lab/HLDC

Abstract

Linearly Transformed Cosines (LTCs) are a family of distributions that are used for real-time area-light shading thanks to their analytic integration properties. Modern game engines use an LTC approximation of the ubiquitous GGX model, but currently this approximation only exists for isotropic GGX and thus anisotropic GGX is not supported. While the higher dimensionality presents a challenge in itself, we show that several additional problems arise when fitting, post-processing, storing, and interpolating LTCs in the anisotropic case. Each of these operations must be done carefully to avoid rendering artifacts. We find robust solutions for each operation by introducing and exploiting invariance properties of LTCs. As a result, we obtain a small 84 look-up table that provides a plausible and artifact-free LTC approximation to anisotropic GGX and brings it to real-time area-light shading.

Abstract

Histopathology image analysis is widely accepted as a gold standard for cancer diagnosis. The Cancer Genome Atlas (TCGA) contains large repositories of histopathology whole slide images spanning several organs and subtypes. However, not much work has gone into analyzing all the organs and subtypes and their similarities. Our work attempts to bridge this gap by training deep learning models to classify cancer vs. normal patches for 11 subtypes spanning seven organs (9,792 tissue slides) to achieve high classification performance. We used these models to investigate their performances in the test set of other organs (cross-organ inference). We found that every model had a good cross-organ inference accuracy when tested on breast, colorectal, and liver cancers. Further, high accuracy is observed between models trained on the cancer subtypes originating from the same organ (kidney and lung). We also validated these performances by showing the separability of cancer and normal samples in a high-dimensional feature space. We further hypothesized that the high cross-organ inferences are due to shared tumor morphologies among organs. We validated the hypothesis by showing the overlap in the Gradient-weighted Class Activation Mapping (GradCAM) visualizations and similarities in the distributions of nuclei features present within the high-attention regions.

Abstract

Effective design of autopilots for fixed-wing unmanned aerial vehicles (UAVs) is still a great challenge, due to unmodeled effects and uncertainties that these vehi- cles exhibit during flight. Unmodeled effects and uncertain- ties comprise longitudinal/lateral cross-couplings, as well as poor knowledge of equilibrium points (trimming points) of the UAV dynamics. The main contribution of this article is a new adaptive autopilot design, based on uncertain Euler–Lagrange dynamics of the UAV and where the control can explicitly take into account under-actuation in the dy- namics, reduced structural knowledge of cross-couplings and trimming points. This system uncertainty is handled via appropriately designed adaptive laws: stability of the con- trolled UAV is analyzed. Hardware-in-the-loop tests, com- parisons with an Ardupilot autopilot and with a robustified autopilot validate the effectiveness of the control design, even in the presence of strong saturation of the UAV actua- tors.

Abstract

Quadrotors find a vast potential use in delivery and disaster relief operations. Control becomes critical in such sce- narios, especially when quadrotors have to manoeuvre through constrained spaces or deliver payloads at precise locations in the presence of external disturbances and parametric uncertainties stemming from uncertain payloads. Therefore, the controller has to guarantee a predefined tracking accuracy not to violate the state constraints. On the other hand, conventional fixed-valued state constraints are not suitable in many scenarios such as (i) initial offset being well beyond the expected accuracy, (ii) system dynam- ics experiencing significant transients due to the dropping of the payload. However, to the best of the authors’ knowledge, state- of-the-art controllers do not provide any solution for an underac- tuated system like a quadrotor when the system needs to honour time-varying constraints under uncertainties. This work proposes a controller for quadrotors which is robust against external distur- bances and parametric variations and guarantees a time-varying predefined position, velocity, attitude, and attitude-rate accuracy. The closed-loop system stability is established analytically, and the effectiveness of the proposed controller is validated experimentally compared to the state-of-the-art under a precision payload delivery scenario.

Abstract

Drought, a natural disaster, occurs in all types of climate. Temperature, wind, relative humidity, rainfall intensity and rainfall duration play a significant part in the phenomenon of droughts. It affects natural sources of water and also can reduce the water supply, quality of water, crop yield, as well as the economy and social activities. Drought is an extreme event that affects natural resources, environment and society for a long time. Usually, drought occurs gradually; but it can be more terrible than floods. Meteorological, hydrological and agricultural are its broad types as described in Fig. [1]. Out of these, meteorological drought, defined as an abnormal shortage of precipitation, is the main cause of all other types of droughts. Drought index measures the levels of drought by acquiring data into a single numerical value from one or more hydrological variables. Several drought indices are found to assess the change in climatic variables. Those are Palmer Drought Severity Index, Crop Moisture Index, Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI) and Reconnaissance Drought Index (RDI) [1]. Based on the drought studies, almost all drought indices use precipitation as the sole variable or with the other hydrological elements, as per the type of demand, which is indicated by WMO [2]. There have been many attempts over the last few decades to develop a new drought index on the basis of a climatological precipitation study [1, 3, 4]. Vicente-Serrano et al. [5] proposed a new evapotranspiration-based index which is Standardized Precipitation Evapotranspiration Index (SPEI) based on the calculation of Potential Evapotranspiration.

Abstract

Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the adaptation stage. In this paper, we present a self-training based source-free video domain adaptation approach (without bells and whistles) to address this challenge by bridging the gap between the source and the target domains. We use the source pre-trained model to generate pseudo-labels for the target domain samples, which are inevitably noisy. We treat the problem of source-free video domain adaptation as learning from noisy labels and argue that the samples with correct pseudo-labels can help in the adaptation stage. To this end, we leverage the crossentropy loss as an indicator of the correctness of pseudo-labels, and use the resulting small-loss samples from the target domain for fine-tuning the model. Extensive experimental evaluations show that our method termed as CleanAdapt achieves ∼ 7% gain over the source-only model and outperforms the state-of-the-art approaches on various open datasets.

Abstract

Deep neural networks suffer from Catastrophic Forgetting (CF) on old tasks when they are trained to learn new tasks sequentially, since the parameters of the model will change to optimize on the new class. The problem of alleviating CF is of interest to Computer aided diagnostic (CAD) sys- tems community to facilitate class incremental learning (IL): learn new classes as and when new data/annotations are made available and old data is no longer accessible. However, IL has not been explored much in CAD development. We pro- pose a novel approach that ensures that a model remembers the causal factor behind the decisions on the old classes, while incrementally learning new classes. We introduce a common auxiliary task during the course of incremental training, whose hidden representations are shared across all the classification heads. Since the hidden representation is no longer task-specific, it leads to a significant reduction in CF. We demonstrate our approach by incrementally learning 5 different tasks on Chest-Xrays and compare the results with the state-of-the-art regularization methods. Our approach performs consistently well in reducing CF in all the tasks with almost zero CF in most of the cases unlike standard regularisation-based approaches.

Abstract

Segmentation and analysis of sub-cortical structures is of interest in diagnosing some neurological diseases. Segmentation is a challenging task because of brain tissue ambiguity and data scarcity. Deep learning (DL) solutions are widely used for this purpose by considering the problem as a semantic segmentation of the brain. In general, DL approaches exhibit a bias towards larger structures when training is done on the whole brain. We propose a method to address this problem wherein a pre-training step is used to learn tissue characteristics and a rough ROI extraction step aids focusing on local context. We use a Residual U-net for demonstrating the proposed method. Experiments on the IBSR and MICCAI datasets show that our proposed solution leads to an improvement in segmentation performance in general with medium and small size structures benefiting significantly. The performance with the proposed method is also marginally better than a more complex, state of art sub-cortical structure segmentation method. A strength of the proposed method is that it can also be applied as a modification to any existing segmentation solution.

Abstract

Bluetooth technology has enabled short-range wireless communication for billions of devices. Bluetooth Low-Energy (BLE) variant aims at improving power consumption on battery-constrained devices. BLE-enabled devices broadcast information (e.g., as beacons) to nearby devices via advertisements. Unfortunately, such functionality can become a double-edged sword at the hands of attackers. In this paper, we primarily show how an attacker can exploit BLE advertisements to exfiltrate information from BLE-enable devices. In particular, our attack establishes a communication medium between two devices without requiring any prior authentication or pairing. We develop a proof-of-concept attack framework on the Android ecosystem and assess its performance via a thorough set of experiments. Our results indicate that such an exfiltration attack is indeed possible though with a limited data rate. Nevertheless, we also demonstrate potential use cases and enhancements to our attack that can further its severeness. Finally, we discuss possible countermeasures to prevent such an attack.