no code implementations • 3 Apr 2024 • Tomoyoshi Kimura, Jinyang Li, Tianshi Wang, Denizhan Kara, Yizhuo Chen, Yigong Hu, Ruijie Wang, Maggie Wigness, Shengzhong Liu, Mani Srivastava, Suhas Diggavi, Tarek Abdelzaher
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a class of) IoT applications.
no code implementations • 28 Mar 2024 • Xiaomin Ouyang, Mani Srivastava
To answer this question, we design an effective prompting framework for LLMs on high-level reasoning tasks, which can handle traces from the raw sensor data as well as the low-level perception results.
1 code implementation • 21 Feb 2024 • Ho Lyun Jeong, Ziqi Wang, Colin Samplawski, Jason Wu, Shiwei Fang, Lance M. Kaplan, Deepak Ganesan, Benjamin Marlin, Mani Srivastava
Constantly locating moving objects, i. e., geospatial tracking, is essential for autonomous building infrastructure.
1 code implementation • NeurIPS 2023 • Shengzhong Liu, Tomoyoshi Kimura, Dongxin Liu, Ruijie Wang, Jinyang Li, Suhas Diggavi, Mani Srivastava, Tarek Abdelzaher
Existing multimodal contrastive frameworks mostly rely on the shared information between sensory modalities, but do not explicitly consider the exclusive modality information that could be critical to understanding the underlying sensing physics.
no code implementations • 14 Oct 2023 • Huatao Xu, Liying Han, Qirui Yang, Mo Li, Mani Srivastava
Recent developments in Large Language Models (LLMs) have demonstrated their remarkable capabilities across a range of tasks.
no code implementations • 24 Jul 2023 • Yi Han, Matthew Chan, Eric Wengrowski, Zhuohuan Li, Nils Ole Tippenhauer, Mani Srivastava, Saman Zonouz, Luis Garcia
We demonstrate that the dynamic nature of EvilEye enables attackers to adapt adversarial examples across a variety of objects with a significantly higher ASR compared to state-of-the-art physical world attack frameworks.
no code implementations • 4 Jun 2023 • Colin Samplawski, Shiwei Fang, Ziqi Wang, Deepak Ganesan, Mani Srivastava, Benjamin M. Marlin
Visual object tracking has seen significant progress in recent years.
1 code implementation • 10 Apr 2023 • Sandeep Singh Sandha, Bharathan Balaji, Luis Garcia, Mani Srivastava
Existing approaches for autonomous control of pan-tilt-zoom (PTZ) cameras use multiple stages where object detection and localization are performed separately from the control of the PTZ mechanisms.
no code implementations • CVPR 2023 • Akash Deep Singh, Yunhao Ba, Ankur Sarker, Howard Zhang, Achuta Kadambi, Stefano Soatto, Mani Srivastava, Alex Wong
To fuse radar depth with an image, we propose a gated fusion scheme that accounts for the confidence scores of the correspondence so that we selectively combine radar and camera embeddings to yield a dense depth map.
no code implementations • 28 Jun 2022 • Pengrui Quan, Supriyo Chakraborty, Jeya Vikranth Jeyakumar, Mani Srivastava
A variety of explanation methods have been proposed in recent years to help users gain insights into the results returned by neural networks, which are otherwise complex and opaque black-boxes.
no code implementations • 21 Jun 2022 • Jeya Vikranth Jeyakumar, Luke Dickens, Luis Garcia, Yu-Hsi Cheng, Diego Ramirez Echavarria, Joseph Noor, Alessandra Russo, Lance Kaplan, Erik Blasch, Mani Srivastava
CoDEx identifies a rich set of complex concept abstractions from natural language explanations of videos-obviating the need to predefine the amorphous set of concepts.
no code implementations • 29 May 2022 • Swapnil Sayan Saha, Sandeep Singh Sandha, Mani Srivastava
We characterize a closed-loop widely applicable workflow of machine learning model development for microcontroller class devices and show that several classes of applications adopt a specific instance of it.
no code implementations • 25 Apr 2022 • Moustafa Alzantot, Luis Garcia, Mani Srivastava
Generative models such as the variational autoencoder (VAE) and the generative adversarial networks (GAN) have proven to be incredibly powerful for the generation of synthetic data that preserves statistical properties and utility of real-world datasets, especially in the context of image and natural language text.
no code implementations • 7 Mar 2022 • Jeya Vikranth Jeyakumar, Ludmila Cherkasova, Saina Lajevardi, Moray Allan, Yue Zhao, John Fry, Mani Srivastava
In this work, we design a novel, scalable approach, where a general demand forecasting model is built using the combined data of all the companies with a normalization factor.
no code implementations • 15 Oct 2021 • Marc Roig Vilamala, Tianwei Xing, Harrison Taylor, Luis Garcia, Mani Srivastava, Lance Kaplan, Alun Preece, Angelika Kimmig, Federico Cerutti
We also demonstrate that our approach is capable of training even with a dataset that has a moderate proportion of noisy data.
no code implementations • 31 Jan 2021 • Pengrui Quan, Ruiming Guo, Mani Srivastava
Recently, there has been a large amount of work towards fooling deep-learning-based classifiers, particularly for images, via adversarial inputs that are visually similar to the benign examples.
2 code implementations • NeurIPS 2020 • Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, Mani Srivastava
Explaining the inner workings of deep neural network models have received considerable attention in recent years.
no code implementations • 27 Oct 2020 • Katie Barrett-Powell, Jack Furby, Liam Hiley, Marc Roig Vilamala, Harrison Taylor, Federico Cerutti, Alun Preece, Tianwei Xing, Luis Garcia, Mani Srivastava, Dave Braines
We present an experimentation platform for coalition situational understanding research that highlights capabilities in explainable artificial intelligence/machine learning (AI/ML) and integration of symbolic and subsymbolic AI/ML approaches for event processing.
BIG-bench Machine Learning Explainable artificial intelligence
no code implementations • 23 Oct 2020 • Dave Braines, Federico Cerutti, Marc Roig Vilamala, Mani Srivastava, Lance Kaplan Alun Preece, Gavin Pearson
Future coalition operations can be substantially augmented through agile teaming between human and machine agents, but in a coalition context these agents may be unfamiliar to the human users and expected to operate in a broad set of scenarios rather than being narrowly defined for particular purposes.
no code implementations • 7 Sep 2020 • Marc Roig Vilamala, Harrison Taylor, Tianwei Xing, Luis Garcia, Mani Srivastava, Lance Kaplan, Alun Preece, Angelika Kimmig, Federico Cerutti
We demonstrate this comparing our approach against a pure neural network approach on a dataset based on Urban Sounds 8K.
no code implementations • 18 Jul 2020 • Bo-Jhang Ho, Bharathan Balaji, Mehmet Koseoglu, Sandeep Sandha, Siyou Pei, Mani Srivastava
Human attention is a scarce resource in modern computing.
1 code implementation • 22 May 2020 • Sandeep Singh Sandha, Mohit Aggarwal, Igor Fedorov, Mani Srivastava
Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually.
no code implementations • 18 Nov 2019 • Xijie Huang, Moustafa Alzantot, Mani Srivastava
NeuronInspect first identifies the existence of backdoor attack targets by generating the explanation heatmap of the output layer.
no code implementations • 5 Aug 2019 • Moustafa Alzantot, Amy Widdicombe, Simon Julier, Mani Srivastava
When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model.
3 code implementations • 28 May 2018 • Moustafa Alzantot, Yash Sharma, Supriyo Chakraborty, huan zhang, Cho-Jui Hsieh, Mani Srivastava
Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches.
5 code implementations • EMNLP 2018 • Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani Srivastava, Kai-Wei Chang
Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify.
1 code implementation • 2 Jan 2018 • Moustafa Alzantot, Bharathan Balaji, Mani Srivastava
Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 10 Nov 2017 • Amr Alanwar, Henrique Ferraz, Kevin Hsieh, Rohit Thazhath, Paul Martin, Joao Hespanha, Mani Srivastava
Therefore, we propose D-SLATS, a framework comprised of three different and independent algorithms to jointly solve time synchronization and localization problems in a distributed fashion.
no code implementations • 15 Jul 2017 • Jeng-Hau Lin, Tianwei Xing, Ritchie Zhao, Zhiru Zhang, Mani Srivastava, Zhuowen Tu, Rajesh K. Gupta
State-of-the-art convolutional neural networks are enormously costly in both compute and memory, demanding massively parallel GPUs for execution.
2 code implementations • 20 Sep 2014 • Jack Kelly, Nipun Batra, Oliver Parson, Haimonti Dutta, William Knottenbelt, Alex Rogers, Amarjeet Singh, Mani Srivastava
In this demonstration, we present an open source toolkit for evaluating non-intrusive load monitoring research; a field which aims to disaggregate a household's total electricity consumption into individual appliances.
Other Computer Science
2 code implementations • 15 Apr 2014 • Nipun Batra, Jack Kelly, Oliver Parson, Haimonti Dutta, William Knottenbelt, Alex Rogers, Amarjeet Singh, Mani Srivastava
We demonstrate the range of reproducible analyses which are made possible by our toolkit, including the analysis of six publicly available data sets and the evaluation of both benchmark disaggregation algorithms across such data sets.
Applications