Abstract

Multiple parallel attention mechanisms that use multiple attention heads facilitate greater performance of the Transformer model for various applications e.g., Neural Machine Translation (NMT), text classification. In multi-head attention mechanism, different heads attend to different parts of the input. However, the limitation is that multiple heads might attend to the same part of the input, resulting in multiple heads being redundant. Thus, the model resources are under-utilized. One approach to avoid this is to prune least important heads based on certain importance score. In this work, we focus on designing a Dynamic Head Importance Computation Mechanism (DHICM) to dynamically calculate the importance of a head with respect to the input. Our insight is to design an additional attention layer together with multi-head attention, and utilize the outputs of the multi-head attention along with the input, to compute the importance for each head. Additionally, we add an extra loss function to prevent the model from assigning same score to all heads, to identify more important heads and improvise performance. We analyzed performance of DHICM for NMT with different languages. Experiments on different datasets show that DHICM outperforms traditional Transformer-based approach by large margin, especially, when less training data is available.

Abstract

The extensive rise in consumption of online social media (OSMs) by a large number of people poses a critical problem of curbing the spread of hateful content on these platforms. With the growing usage of OSMs in multiple languages, the task of detecting and characterizing hate becomes more complex. The subtle variations of code-mixed texts along with switching scripts only add to the complexity. This paper presents a solution for the HASOC 2021 Multilingual Twitter Hate-Speech Detection challenge by team PreCog IIIT Hyderabad. We adopt a multilingual transformer based approach and describe our architecture for all 6 sub-tasks as part of the challenge. Out of the 6 teams that participated in all the sub tasks, our submissions rank 3rd overall.

Abstract

Social media platforms have democratized the publication process resulting into easy and viral propagation of information. Oftentimes this misinformation is accompanied by misleading or doctored images that quickly circulate across the internet and reach many unsuspecting users. Several manual as well as automated efforts have been undertaken in the past to solve this critical problem. While manual efforts cannot keep up with the rate at which this content is churned out, many automated approaches only leverage concatenation (of the image and text representations) thereby failing to build effective crossmodal embeddings. Architectures like this fail in many cases because the text or image doesn’t need to be false for the corresponding text, image pair to be misinformation. While some recent work attempts to use attention techniques to compute a crossmodal representation using pretrained text and image embeddings, we show a more effective approach towards utilizing such pretrained embeddings to build richer representations that can be classified better. This involves several challenges like how to handle text variations on Twitter and Weibo, how to encode the image information and how to leverage the text and image encodings together effectively. Our architecture, SCATE (Shared Cross Attention Transformer Encoders), leverages deep convolutional neural networks and transformer-based methods to encode image and text information utilizing crossmodal attention and shared layers for the two modalities. Our experiments with three popular benchmark datasets (Twitter, WeiboA and WeiboB) show that our proposed methods outperform the state-of-the-art meth

Abstract

Early detection of cardiovascular diseases is crucial for effective treatment and an electrocardiogram (ECG) is pivotal for diagnosis. The accuracy of Deep Learning based methods for ECG signal classification has progressed in recent years to reach cardiologist-level performance. In clinical settings, a cardiologist makes a diagnosis based on the standard 12-channel ECG recording. Automatic analysis of ECG recordings from a multiple-channel perspective has not been given enough attention, so it is essential to analyze an ECG recording from a multiple-channel perspective. We propose a model that leverages the multiple-channel information available in the standard 12-channel ECG recordings and learns patterns at the beat, rhythm, and channel level. The experimental results show that our model achieved a macro-averaged ROC-AUC score of 0.9216, mean accuracy of 88.85% and a maximum F1 score of 0.8057 on the PTB-XL dataset. The attention visualization results from the interpretable model are compared against the cardiologist’s guidelines to validate the correctness and usability

Abstract

Long standing challenges in adaptive bipedal walking control (i.e. control taking care of unknown robot parameters) were to unify the control design instead of designing multiple controllers for different walking phases as well as to bypass computing constraint forces, since it often leads to complex designs. A few attempts to design a single controller for all walking phases ignored or oversimplified the constraint forces. However, these forces are state-dependent and may lead to conservative performance or instability if not countered properly. This work proposes an innovative adaptive control method, based on artificial time delay control, which covers the entire bipedal walking phase and provides robustness against state-dependent unmodelled dynamics such as constraint forces and external impulsive forces arising during walking. Studies using a high fidelity simulator under various forms of disturbances show the effectiveness of the proposed design over the state of the art.

Abstract

A crucial challenge in maintaining formation in an autonomous vehicle platoon rests on designing a suitable control scheme that can tackle external disturbances and uncertain system parameters, especially the friction forces between wheel and ground, which vary with change in road surface, wear in tires and speed of the vehicle. State-of-the-art adaptive controller negotiating such uncertainties can typically handle a priori bounded (or non state-dependent) uncertainties. However, besides the difficulty in accurate modelling and identification of frictional forces, in general, these forces are state-dependent and cannot be a priori bounded (e.g., viscous friction). This paper proposes an adaptive sliding mode controller for nonholonomic wheeled mobile robot based vehicle platoon which can handle unknown complex behaviour of frictional forces without a priori knowledge of its parameters and structures. The effectiveness of the proposed controller is verified in Gazebo simulation in comparison with the state of the art.

Abstract

A major challenge that deep learning systems face is the Catastrophic Forgetting (CF) phenomenon that is observed when finetuning is used to try and adapt a system to a new task or a sequence of datasets with different distributions. CF refers to the significant degradation in performance on the old task/dataset. In this paper, a novel approach is proposed to address CF in computer aided diagnosis (CAD) system design in the medical domain. CAD systems often need to handle a sequence of datasets collected over time from different sites with different imaging parameters/populations. The solution we propose is to move samples from all the datasets closer to a common manifold via a reformer at the front end of a CAD system. The utility of this approach is demonstrated on two common tasks, namely segmentation and classification, using publicly available datasets. Results of extensive experiments show that manifold learning can yield about 74% improvement on an average in the reduction of CF over the baseline fine-tuning process and the state-of-the-art regularization based methods. The results also indicate that a Reformer when used in conjunction with the state-of-the-art regularization methods, has the potential to yield further improvement in CF reduction.

Abstract

Traditionally, video conferencing is a widely adopted solution for telecommunication, but a lack of immersiveness comes inherently due to the 2D nature of facial representation. The integration of Virtual Reality (VR) in a communication/telepresence system through Head Mounted Displays (HMDs) promises to provide users a much better immersive experience. However, HMDs cause hindrance by blocking the facial appearance and expressions of the user. To overcome these issues, we propose a novel attention-enabled encoder-decoder architecture for HMD de-occlusion. We also propose to train our person-specific model using short videos (1-2 minutes) of the user, captured in varying appearances, and demonstrated generalization to unseen poses and appearances of the user. We report superior qualitative and quantitative results over state-of-the-art methods. We also present applications of this approach to hybrid video teleconferencing using existing animation and 3D face reconstruction pipelines.

Abstract

This paper focuses on designing a low-cost and robust IoT-based TDS measurement system for the smart campus. The objective of this low-cost design problem is to find a solution that guarantees precise and uninterrupted output data. The dynamic reading of data, storage capacity, and calibration errors of sensors are the major challenges for IoT-based TDS measurement systems. These challenges are combated in the proposed design using a non-invasive mechanism for data collection, wireless connectivity to the data server, and machine learning calibration of sensor nodes. The TDS data of various water stations located inside the campus is used for the experimental study to develop a regression model for temperature compensation and calibration. The value of TDS sensor voltage variation against temperature is analyzed. The evaluation of the model was performed based on the R 2 and the root mean square error. By using 3 rd degree polynomial regression, we have obtained an R 2 value of 93.96 % and an RMSE of 27.93

Abstract

In Quantum secret sharing we can share both quantum and classical secrets with a quantum resource. In this article we study the problem of revocation of quantum secret shared by the dealer with two shareholders in a three party scenario. In the existing secret sharing protocols there are no means by which the dealer can retrieve back the secret once he/she finds all the share holders to be dishonest. Our protocol makes a significant advancement in solving this problem by designing strategy in bringing back the secret in the worst possible situation when all the shareholders/receivers are dishonest1. In our proposed strategy the dealer also possesses a quantum share of the secret which empowers the dealer to bring back the secret even after sharing is done. However the protocol along with the revocation process also ensures the normal reconstruction at the share holder’s location when they are honest. This advantage comes with the expense of extra one qubit on dealer’s side and consequently we require a four qubit resource to start with for 1-dealer and 2-share holder’s scenario. Here in this article we not only give the description of our protocol but also give an example where our protocol is working with the help of a four qubit entangled state. We also explicitly found out the range of parameter for the input state for which the protocol will be successful.