Raunak Sinha

Bio: Raunak Sinha is an academic researcher from Indraprastha Institute of Information Technology. The author has contributed to research in topics: Kinship & Deep learning. The author has co-authored 3 publications.

FamilyGAN: Generating Kin Face Images Using Generative Adversarial Networks

Abstract: Automatic kinship verification using face images involves analyzing features and computing similarities between two input images to establish kin-relationship. It has gained significant interest from the research community and several approaches including deep learning architectures are proposed. One of the law enforcement applications of kinship analysis involves predicting the kin image given an input image. In other words, the question posed here is: “given an input image, can we generate a kin-image?” This paper attempts to generate kin-images using Generative Adversarial Learning for multiple kin-relations. The proposed FamilyGAN model incorporates three information, kin-gender, kinship loss, and reconstruction loss, in a GAN model to generate kin images. FamilyGAN is the first model capable of generating kin-images for multiple relations such as parent-child and siblings from a single model. On the WVU Kinship Video database, the proposed model shows very promising results for generating kin images. Experimental results show 71.34% kinship verification accuracy using the images generated via FamilyGAN.

AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework

Abstract: Generative models are becoming increasingly popular in the literature, with Generative Adversarial Networks (GAN) being the most successful variant, yet. With this increasing demand and popularity, it is becoming equally difficult and challenging to implement and consume GAN models. A qualitative user survey conducted across 47 practitioners show that expert level skill is required to use GAN model for a given task, despite the presence of various open source libraries. In this research, we propose a novel system called AuthorGAN, aiming to achieve true democratization of GAN authoring. A highly modularized library agnostic representation of GAN model is defined to enable interoperability of GAN architecture across different libraries such as Keras, Tensorflow, and PyTorch. An intuitive drag-and-drop based visual designer is built using node-red platform to enable custom architecture designing without the need for writing any code. Five different GAN models are implemented as a part of this framework and the performance of the different GAN models are shown using the benchmark MNIST dataset.

Facial Kinship Verification: A Comprehensive Review and Outlook

Abstract: Abstract The goal of Facial Kinship Verification (FKV) is to automatically determine whether two individuals have a kin relationship or not from their given facial images or videos. It is an emerging and challenging problem that has attracted increasing attention due to its practical applications. Over the past decade, significant progress has been achieved in this new field. Handcrafted features and deep learning techniques have been widely studied in FKV. The goal of this paper is to conduct a comprehensive review of the problem of FKV. We cover different aspects of the research, including problem definition, challenges, applications, benchmark datasets, a taxonomy of existing methods, and state-of-the-art performance. In retrospect of what has been achieved so far, we identify gaps in current research and discuss potential future research directions.

KinStyle: A Strong Baseline Photorealistic Kinship Face Synthesis with an Optimized StyleGAN Encoder

Abstract: High-fidelity kinship face synthesis is a challenging task due to the limited amount of kinship data available for training and low-quality images. In addition, it is also hard to trace the genetic traits between parents and children from those low-quality training images. To address these issues, we leverage the pre-trained state-of-the-art face synthesis model, StyleGAN2, for kinship face synthesis. To handle large age, gender and other attribute variations between the parents and their children, we conduct a thorough study of its rich latent spaces and different encoder architectures for an optimized encoder design to repurpose StyleGAN2 for kinship face synthesis. The obtained latent representation from our developed encoder pipeline with stage-wise training strikes a better balance of editability and synthesis fidelity for identity preserving and attribute manipulations than other compared approaches. With extensive subjective, quantitative, and qualitative evaluations, the proposed approach consistently achieves better performance in terms of facial attribute heredity and image generation fidelity than other compared state-of-the-art methods. This demonstrates the effectiveness of the proposed approach which can yield promising and satisfactory kinship face synthesis using only a single and straightforward encoder architecture.

Implementing and Deploying an ML Pipeline for IoT Intrusion Detection with Node-RED

Abstract: Edge devices in IoT ecosystems are subject to cyber-attacks (either as targets or participants), and the use of Machine Learning (ML) in said devices can facilitate intrusion detection locally, reducing the reliance on cloud infrastructure and increasing data privacy. This paper describes the implementation of an IoT-oriented application (use-case) that leverages ML on the edge, namely on the router deployed by an Internet Service Provider (ISP) at the customer premises, to detect potentially malicious traffic involving the customer’s IoT nodes. We evaluate several middleware solutions regarding their support for ML applications in embedded devices, with a focus on low-code and event-driven approaches. We report the challenges and lessons learned in transferring an ML pipeline for intrusion detection, originally developed in a native Linux system, to a description in the selected middleware, Node-RED. Most of the processing itself is assured by the services of the original implementation, while Node-RED essentially acts as a control plane for coordinating those services. We also describe the deployment of the ML pipeline based on Node-RED on the edge device (router), and provide a characterization of the resulting solution.