Abstract

Enabling effective brain-computer interfaces requires understanding how the human brain encodes stimuli across modalities such as visual, language (or text), etc. Brain encoding aims at constructing fMRI brain activity given a stimulus. There exists a plethora of neural encoding models which study brain encoding for single mode stimuli: visual (pretrained CNNs) or text (pretrained language models). Few recent papers have also obtained separate visual and text representation models and performed late-fusion using simple heuristics. However, previous work has failed to explore: (a) the effectiveness of image Transformer models for encoding visual stimuli, and (b) co-attentive multi-modal modeling for visual and text reasoning. In this paper, we systematically explore the efficacy of image Transformers (ViT, DEiT, and BEiT) and multi-modal Transformers (VisualBERT, LXMERT, and CLIP) for brain encoding. Extensive experiments on two popular datasets, BOLD5000 and Pereira, provide the following insights. (1) To the best of our knowledge, we are the first to investigate the effectiveness of image and multi-modal Transformers for brain encoding. (2) We find that VisualBERT, a multi-modal Transformer, significantly outperforms previously proposed single-mode CNNs, image Transformers as well as other previously proposed multi-modal models, thereby establishing new state-of-theart. The supremacy of visio-linguistic models raises the question of whether the responses elicited in the visual regions are affected implicitly by linguistic processing even when passively viewing images. Future fMRI tasks can verify this computational insight in an appropriate experimental setting.

Abstract

Sepsis is a leading cause of mortality and its treatment is very expensive. Sepsis treatment is also very challenging because there is no consensus on what interventions work best and different patients respond very differently to the same treatment. Deep Reinforcement Learning methods can be used to come up with optimal policies for treatment strategies mirroring physician actions. In the healthcare scenario, the available data is mostly collected offline with no interaction with the environment, which necessitates the use of offline RL techniques. The Offline RL paradigm suffers from action distribution shifts which in turn negatively affects learning an optimal policy for the treatment. In this work, a Conservative-Q Learning (CQL) algorithm is used to mitigate this shift and its corresponding policy reaches closer to the physicians policy than conventional deep Q Learning. The policy learned could help clinicians in Intensive Care Units to make better decisions while treating septic patients and improve survival rate.

Abstract

Cryptocurrencies are poised to revolutionize the modern economy by democratizing commerce. These currencies operate on top of blockchain-based distributed ledgers. Existing permissionless blockchain-based protocols offer unparalleled benefits like decentralization, anonymity, and transparency. However, these protocols suffer in performance which hinders their widespread adoption. In particular, high time-to-finality and low transaction rates keep them from replacing centralized payment systems such as the Visa network. Permissioned blockchain protocols offer attractive performance guarantees, but they are not considered suitable for deploying decentralized cryptocurrencies due to their centralized nature. Researchers have developed several multi-layered blockchain protocols that combine both permissioned and permissionless blockchain protocols to achieve high performance along with decentralization. The key idea with existing layered blockchain protocols in literature is to divide blockchain operations into two layers and use different types of blockchain protocols to manage each layer. However, many such works come with the assumptions of honest majority which may not accurately reflect the real world where the participants may be self-interested or rational. These assumptions may render the protocols susceptible to security threats in the real world, as highlighted by the literature focused on exploring game-theoretic attacks on these protocols. We generalize the “layered” approach taken by existing protocols in the literature and present a framework to analyze the system in the BAR Model and provide a generalized game-theoretic analysis of such protocols. Using our analysis, we identify the critical system parameters required for a distributed ledger’s secure operation in a more realistic setting.

Abstract

The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting approaches. Specifically, the approaches exhibit unacceptably large standard deviation wrt statistical measures (MSE, MAE). To address such concerns in a holistic manner, we make two fundamental contributions. Firstly, we modify the training pipeline to accommodate the knowledge of dataset skew. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian binning approach. More specifically, we propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage binaware optimization. As the second contribution, we introduce additional performance measures which are more inclusive and throw light on various comparative performance aspects of the deep networks. We also show that our binning-based modifications retain their superiority wrt the newly proposed performance measures. Overall, our contributions enable a practically useful and detail-oriented characterization of performance for crowd counting approaches.

Abstract

Multi-object multi-part scene parsing is a challenging task which requires detecting multiple object classes in a scene and segmenting the semantic parts within each object. In this paper, we propose FLOAT, a factorized label space framework for scalable multi-object multi-part parsing. Our framework involves independent dense prediction of object category and part attributes which increases scalability and reduces task complexity compared to the monolithic label space counterpart. In addition, we propose an inference-time ‘zoom’ refinement technique which significantly improves segmentation quality, especially for smaller objects/parts. Compared to state of the art, FLOAT obtains an absolute improvement of 2.0% for mean IOU (mIOU) and 4.8% for segmentation quality IOU (sqIOU) on the Pascal-Part-58 dataset. For the larger Pascal-Part-108 dataset, the improvements are 2.1% for mIOU and 3.9% for

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

In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles. Identifying and penalizing such riders is vital in curbing road accidents and improving citizens’ safety. With this motivation, we propose an approach for detecting, tracking, and counting motorcycle riding violations in videos taken from a vehicle-mounted dashboard camera. We employ a curriculum learning-based object detector to better tackle challenging scenarios such as occlusions. We introduce a novel trapezium-shaped object boundary representation to increase robustness and tackle the rider-motorcycle association. We also introduce an amodal regressor that generates bounding boxes for the occluded riders. Experimental results on a large-scale unconstrained driving dataset demonstrate the superiority of our approach compared to existing approaches and other ablative variants.

Abstract

The variability of clinical course and prognosis of COVID-19 highlights the necessity of patient sub-group risk stratification based on clinical data. In this study, clinical data from a cohort of Indian COVID-19 hospitalized patients is used to develop risk stratification and mortality prediction models. We analyzed a set of 70 clinical parameters including physiological and hematological for developing machine learning models to identify biomarkers. We also compared the Indian and Wuhan cohort, and analyzed the role of steroids. A bootstrap averaged ensemble of Bayesian networks was also learned to construct an explainable model for discovering actionable influences on mortality and days to outcome. We discovered blood parameters, diabetes, co-morbidity and SpO2 levels as important risk stratification features, whereas mortality prediction is dependent only on blood parameters. XGboost and logistic regression model yielded the best performance on risk stratification and mortality prediction, respectively (AUC score 0.83, AUC score 0.92). Blood coagulation parameters (ferritin, D-Dimer and INR), immune and inflammation parameters IL6, LDH and Neutrophil (%) are common features for both risk and mortality prediction. Compared with Wuhan patients, Indian patients with extreme blood parameters indicated higher survival rate. Analyses of medications suggest that a higher proportion of survivors and mild patients who were administered steroids had extreme neutrophil and lymphocyte percentages. The ensemble averaged Bayesian network structure revealed serum ferritin to be the mos

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