Search Results for author: Nishant Kumar

Found 22 papers, 12 papers with code

Quantile-based Maximum Likelihood Training for Outlier Detection

1 code implementation20 Aug 2023 Masoud Taghikhah, Nishant Kumar, Siniša Šegvić, Abouzar Eslami, Stefan Gumhold

Previous attempts to address this challenge involved training image classifiers through contrastive learning using actual outlier data or synthesizing outliers for self-supervised learning.

Autonomous Driving Contrastive Learning +3

Uncertainty Quantification for Image-based Traffic Prediction across Cities

1 code implementation11 Aug 2023 Alexander Timans, Nina Wiedemann, Nishant Kumar, Ye Hong, Martin Raubal

We compare two epistemic and two aleatoric UQ methods on both temporal and spatio-temporal transfer tasks, and find that meaningful uncertainty estimates can be recovered.

Decision Making Decision Making Under Uncertainty +3

Learning to reconstruct the bubble distribution with conductivity maps using Invertible Neural Networks and Error Diffusion

no code implementations4 Jul 2023 Nishant Kumar, Lukas Krause, Thomas Wondrak, Sven Eckert, Kerstin Eckert, Stefan Gumhold

Electrolysis is crucial for eco-friendly hydrogen production, but gas bubbles generated during the process hinder reactions, reduce cell efficiency, and increase energy consumption.

Examining Computational Performance of Unsupervised Concept Drift Detection: A Survey and Beyond

no code implementations17 Apr 2023 Elias Werner, Nishant Kumar, Matthias Lieber, Sunna Torge, Stefan Gumhold, Wolfgang E. Nagel

We show that the previous works consider computational performance only as a secondary objective and do not have a benchmark for such evaluation.

Benchmarking

Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection

1 code implementation CVPR 2023 Nishant Kumar, Siniša Šegvić, Abouzar Eslami, Stefan Gumhold

However, this strategy does not guarantee that the synthesized outlier features will have a low likelihood according to the other class-conditional Gaussians.

Autonomous Driving Object +2

Enhancing Fairness of Visual Attribute Predictors

1 code implementation7 Jul 2022 Tobias Hänel, Nishant Kumar, Dmitrij Schlesinger, Mengze Li, Erdem Ünal, Abouzar Eslami, Stefan Gumhold

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes.

Attribute Fairness

TransDrift: Modeling Word-Embedding Drift using Transformer

no code implementations16 Jun 2022 Nishtha Madaan, Prateek Chaudhury, Nishant Kumar, Srikanta Bedathur

In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines.

Word Embeddings

Scalable Robust Federated Learning with Provable Security Guarantees

no code implementations29 Sep 2021 Andrew Liu, Jacky Y. Zhang, Nishant Kumar, Dakshita Khurana, Oluwasanmi O Koyejo

Federated averaging, the most popular aggregation approach in federated learning, is known to be vulnerable to failures and adversarial updates from clients that wish to disrupt training.

Federated Learning

InFlow: Robust outlier detection utilizing Normalizing Flows

1 code implementation10 Jun 2021 Nishant Kumar, Pia Hanfeld, Michael Hecht, Michael Bussmann, Stefan Gumhold, Nico Hoffmann

Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation.

Density Estimation Outlier Detection +1

Bulk Modulus along Jamming Transition Lines of Bidisperse Granular Packings

no code implementations3 Mar 2021 Juan C. Petit, Nishant Kumar, Stefan Luding, Matthias Sperl

We find that the bulk modulus $K$ jumps at $X^{*}_{\mathrm S}(\delta = 0. 15) \approx 0. 21$, at the maximum jamming density, where both particle species mix most efficiently, while for $X_{\mathrm S} < X^{*}_{\mathrm S}$ $K$ is decoupled in two scenarios as a result of the first and second jamming transition.

Soft Condensed Matter

Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey

no code implementations19 Feb 2021 Nishant Kumar, Martin Raubal

In this survey, we present the current state of deep learning applications in the tasks related to detection, prediction, and alleviation of congestion.

HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging

1 code implementation18 Jan 2021 Nikunj Gupta, G Srinivasaraghavan, Swarup Kumar Mohalik, Nishant Kumar, Matthew E. Taylor

This paper considers the case where there is a single, powerful, \emph{central agent} that can observe the entire observation space, and there are multiple, low-powered \emph{local agents} that can only receive local observations and are not able to communicate with each other.

Multi-agent Reinforcement Learning reinforcement-learning +2

FuseVis: Interpreting neural networks for image fusion using per-pixel saliency visualization

1 code implementation6 Dec 2020 Nishant Kumar, Stefan Gumhold

However, it is challenging to analyze the reliability of these CNNs for the image fusion tasks since no groundtruth is available.

Autonomous Driving Multi-Exposure Image Fusion

CrypTFlow2: Practical 2-Party Secure Inference

1 code implementation13 Oct 2020 Deevashwer Rathee, Mayank Rathee, Nishant Kumar, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma

We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation.

Activity-based contact network scaling and epidemic propagation in metropolitan areas

1 code implementation10 Jun 2020 Nishant Kumar, Jimi B. Oke, Bat-hen Nahmias-Biran

Given the growth of urbanization and emerging pandemic threats, more sophisticated models are required to understand disease propagation and investigate the impacts of intervention strategies across various city types.

Physics and Society Populations and Evolution

Visualisation of Medical Image Fusion and Translation for Accurate Diagnosis of High Grade Gliomas

1 code implementation26 Jan 2020 Nishant Kumar, Nico Hoffmann, Matthias Kirsch, Stefan Gumhold

The medical image fusion combines two or more modalities into a single view while medical image translation synthesizes new images and assists in data augmentation.

Data Augmentation Translation

CrypTFlow: Secure TensorFlow Inference

4 code implementations16 Sep 2019 Nishant Kumar, Mayank Rathee, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma

Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity guarantees to convert any semi-honest MPC protocol into an MPC protocol that provides malicious security.

Structural Similarity based Anatomical and Functional Brain Imaging Fusion

1 code implementation11 Aug 2019 Nishant Kumar, Nico Hoffmann, Martin Oelschlägel, Edmund Koch, Matthias Kirsch, Stefan Gumhold

Multimodal medical image fusion helps in combining contrasting features from two or more input imaging modalities to represent fused information in a single image.

SSIM

Drishtikon: An advanced navigational aid system for visually impaired people

no code implementations23 Apr 2019 Shashank Kotyan, Nishant Kumar, Pankaj Kumar Sahu, Venkanna Udutalapally

In this paper, we propose an aid system developed using object detection and depth perceivement to navigate a person without dashing into an object.

Navigate Object +2

U-PC: Unsupervised Planogram Compliance

no code implementations ECCV 2018 Archan Ray, Nishant Kumar, Avishek Shaw, Dipti Prasad Mukherjee

We present an end-to-end solution for recognizing merchandise displayed in the shelves of a supermarket.

Marketing

Using Big Data to Enhance the Bosch Production Line Performance: A Kaggle Challenge

no code implementations29 Dec 2016 Ankita Mangal, Nishant Kumar

This paper describes our approach to the Bosch production line performance challenge run by Kaggle. com.

Cannot find the paper you are looking for? You can Submit a new open access paper.