no code implementations • 27 Jan 2025 • Zhiling Chen, Hanning Chen, Mohsen Imani, Farhad Imani
In industrial settings, the accurate detection of anomalies is essential for maintaining product quality and ensuring operational safety.
no code implementations • 17 Dec 2024 • Wenjun Huang, Yang Ni, Hanning Chen, Yirui He, Ian Bryant, Yezi Liu, Mohsen Imani
Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video.
no code implementations • 4 Dec 2024 • Sungheon Jeong, Hanning Chen, Sanggeon Yun, Suhyeon Cho, Wenjun Huang, Xiangjian Liu, Mohsen Imani
While large-scale datasets have significantly advanced image-based models, the scarcity of comprehensive event datasets has limited performance potential in event modality.
no code implementations • 21 Nov 2024 • Sungheon Jeong, Hamza Errahmouni Barkam, Sanggeon Yun, Yeseong Kim, Shaahin Angizi, Mohsen Imani
Hyperdimensional computing (HDC) enables efficient data encoding and processing in high-dimensional space, benefiting machine learning and data analysis.
no code implementations • 13 Nov 2024 • Sanggeon Yun, Ryozo Masukawa, William Youngwoo Chung, Minhyoung Na, Nathaniel Bastian, Mohsen Imani
This continuous learning approach enhances the robustness of anomaly detection models, making them more suitable for deployment in dynamic and resource-constrained environments.
no code implementations • 2 Nov 2024 • Fardin Jalil Piran, Zhiling Chen, Mohsen Imani, Farhad Imani
Yet, adding DP noise to black-box ML models degrades performance, especially in dynamic IoT systems where continuous, lifelong FL learning accumulates excessive noise over time.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
no code implementations • 30 Oct 2024 • Ryozo Masukawa, Sanggeon Yun, Yoshiki Yamaguchi, Mohsen Imani
Our model generates a GNN-based prompt with image for Large Language Model (LLM), which deliver cost-effective and high-quality video descriptions.
no code implementations • 20 Oct 2024 • Xunzhao Yin, Hamza Errahmouni Barkam, Franz Müller, Yuxiao Jiang, Mohsen Imani, Sukhrob Abdulazhanov, Alptekin Vardar, Nellie Laleni, Zijian Zhao, Jiahui Duan, Zhiguo Shi, Siddharth Joshi, Michael Niemier, Xiaobo Sharon Hu, Cheng Zhuo, Thomas Kämpfe, Kai Ni
To address these challenges-and mitigate the typical data-transfer bottleneck of classical Von Neumann architectures-we propose a ferroelectric charge-domain compute-in-memory (CiM) array as the foundational processing element for neuro-symbolic AI.
1 code implementation • 13 Sep 2024 • Hanning Chen, Yang Ni, Wenjun Huang, Yezi Liu, Sungheon Jeong, Fei Wen, Nathaniel Bastian, Hugo Latapie, Mohsen Imani
We design a new pruning decoder to take both image tokens and vision-language guidance as input to predict the relevance of each image token to the task.
no code implementations • 13 Sep 2024 • Yezi Liu, Hanning Chen, Mohsen Imani
Link prediction is a crucial task in network analysis, but it has been shown to be prone to biased predictions, particularly when links are unfairly predicted between nodes from different sensitive groups.
no code implementations • 1 Sep 2024 • Wenjun Huang, Yang Ni, Arghavan Rezvani, Sungheon Jeong, Hanning Chen, Yezi Liu, Fei Wen, Mohsen Imani
By jointly optimizing a privacy-enhancing module, a privacy recovery module, and a pose estimator, our system ensures robust privacy protection, efficient SPI recovery, and high-performance HPE.
no code implementations • 13 Aug 2024 • Zhiling Chen, Hanning Chen, Mohsen Imani, Ruimin Chen, Farhad Imani
Nonetheless, VLMs face challenges in consistently verifying PPE attributes due to the complexity and variability of workplace environments, requiring them to interpret context-specific language and visual cues simultaneously.
no code implementations • 9 Jul 2024 • Fardin Jalil Piran, Prathyush P. Poduval, Hamza Errahmouni Barkam, Mohsen Imani, Farhad Imani
Machine Learning (ML) models combined with in-situ sensing offer a powerful solution to address defect detection challenges in Additive Manufacturing (AM), yet this integration raises critical data privacy concerns, such as data leakage and sensor data compromise, potentially exposing sensitive information about part design and material composition.
no code implementations • 27 Jun 2024 • Sanggeon Yun, Ryozo Masukawa, Minhyoung Na, Mohsen Imani
In the context of escalating safety concerns across various domains, the tasks of Video Anomaly Detection (VAD) and Video Anomaly Recognition (VAR) have emerged as critically important for applications in intelligent surveillance, evidence investigation, violence alerting, etc.
no code implementations • 13 Jun 2024 • Prathyush Poduval, Zhuowen Zou, Alvaro Velasquez, Mohsen Imani
This paper presents a quantum algorithm for efficiently decoding hypervectors, a crucial process in extracting atomic elements from hypervectors - an essential task in Hyperdimensional Computing (HDC) models for interpretable learning and information retrieval.
no code implementations • 15 May 2024 • Calvin Yeung, Zhuowen Zou, Mohsen Imani
In this work, we introduce the GHRR framework, prove its theoretical properties and its adherence to HDC properties, explore its kernel and binding characteristics, and perform empirical experiments showcasing its flexible non-commutativity, enhanced decoding accuracy for compositional structures, and improved memorization capacity compared to FHRR.
no code implementations • 17 Apr 2024 • Sanggeon Yun, Ryozo Masukawa, Sungheon Jeong, Mohsen Imani
Customizable image retrieval from large datasets remains a critical challenge, particularly when preserving spatial relationships within images.
no code implementations • 20 Mar 2024 • Wenjun Huang, Hanning Chen, Yang Ni, Arghavan Rezvani, Sanggeon Yun, Sungheon Jeon, Eric Pedley, Mohsen Imani
Detecting marine objects inshore presents challenges owing to algorithmic intricacies and complexities in system deployment.
no code implementations • 20 Mar 2024 • Calvin Yeung, Prathyush Poduval, Mohsen Imani
In this work, we introduce a new variant of the resonator network, based on self-attention based update rules in the iterative search problem.
no code implementations • 12 Mar 2024 • Hanning Chen, Wenjun Huang, Yang Ni, Sanggeon Yun, Yezi Liu, Fei Wen, Alvaro Velasquez, Hugo Latapie, Mohsen Imani
Nevertheless, the naive application of VLMs leads to sub-optimal quality, due to the misalignment between embeddings of object images and their visual attributes, which are mainly adjective phrases.
no code implementations • 9 Mar 2024 • Hanning Chen, Yang Ni, Ali Zakeri, Zhuowen Zou, Sanggeon Yun, Fei Wen, Behnam Khaleghi, Narayan Srinivasa, Hugo Latapie, Mohsen Imani
When conducting cross-models and cross-platforms comparison, HDReason yields an average 4. 2x higher performance and 3. 4x better energy efficiency with similar accuracy versus the state-of-the-art FPGA-based GCN training platform.
no code implementations • 17 Feb 2024 • Yang Ni, Zhuowen Zou, Wenjun Huang, Hanning Chen, William Youngwoo Chung, Samuel Cho, Ranganath Krishnan, Pietro Mercati, Mohsen Imani
Drawing inspiration from the outstanding learning capability of our human brains, Hyperdimensional Computing (HDC) emerges as a novel computing paradigm, and it leverages high-dimensional vector presentation and operations for brain-like lightweight Machine Learning (ML).
no code implementations • 3 Feb 2024 • Wenjun Huang, Arghavan Rezvani, Hanning Chen, Yang Ni, Sanggeon Yun, Sungheon Jeong, Mohsen Imani
To enhance the framework's performance, the training process is customized and a "lazy" sensor deactivation strategy utilizing temporal information is introduced.
no code implementations • 4 Jan 2024 • Sanggeon Yun, Hanning Chen, Ryozo Masukawa, Hamza Errahmouni Barkam, Andrew Ding, Wenjun Huang, Arghavan Rezvani, Shaahin Angizi, Mohsen Imani
Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data.
no code implementations • CVPR 2024 • Prathyush Prasanth Poduval, Zhuowen Zou, Mohsen Imani
We address this challenge by proposing the HDC Memorized-Factorization Problem that captures the common patterns of construction in HDC models.
no code implementations • 29 Nov 2023 • Farbin Fayza, Cansu Demirkiran, Hanning Chen, Che-Kai Liu, Avi Mohan, Hamza Errahmouni, Sanggeon Yun, Mohsen Imani, David Zhang, Darius Bunandar, Ajay Joshi
Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN).
no code implementations • 1 Aug 2023 • Sercan Aygun, Mehran Shoushtari Moghadam, M. Hassan Najafi, Mohsen Imani
It zeroes in on the HDC system input and the generation of hypervectors, directly influencing the hypervector encoding process.
no code implementations • 20 Jul 2023 • Hugo Latapie, Shan Yu, Patrick Hammer, Kristinn R. Thorisson, Vahagn Petrosyan, Brandon Kynoch, Alind Khare, Payman Behnam, Alexey Tumanov, Aksheit Saxena, Anish Aralikatti, Hanning Chen, Mohsen Imani, Mike Archbold, Tangrui Li, Pei Wang, Justin Hart
Traditional computer vision models often necessitate extensive data acquisition, annotation, and validation.
1 code implementation • 11 Apr 2023 • Junyao Wang, Sitao Huang, Mohsen Imani
Brain-inspired hyperdimensional computing (HDC) has been recently considered a promising learning approach for resource-constrained devices.
no code implementations • 11 Apr 2023 • Junyao Wang, Hanning Chen, Mariam Issa, Sitao Huang, Mohsen Imani
Cybersecurity has emerged as a critical challenge for the industry.
no code implementations • 1 Aug 2022 • Sina Shahhosseini, Yang Ni, Hamidreza Alikhani, Emad Kasaeyan Naeini, Mohsen Imani, Nikil Dutt, Amir M. Rahmani
Considering the significant role of wearable devices in monitoring human body parameters, on-device learning can be utilized to build personalized models for behavioral and physiological patterns, and provide data privacy for users at the same time.
no code implementations • 8 Jul 2022 • Paul R. Genssler, Hamza E. Barkam, Karthik Pandaram, Mohsen Imani, Hussam Amrouch
The pivotal issue of reliability is one of colossal concern for circuit designers.
no code implementations • 14 May 2022 • Yang Ni, Danny Abraham, Mariam Issa, Yeseong Kim, Pietro Mercati, Mohsen Imani
Our evaluation shows QHD capability for real-time learning, providing 34. 6 times speedup and significantly better quality of learning than DQN.
no code implementations • 1 Oct 2021 • Zhuowen Zou, Haleh Alimohamadi, Farhad Imani, Yeseong Kim, Mohsen Imani
Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (HDC) have shown promising results in enabling efficient and robust cognitive learning.
no code implementations • 10 Aug 2020 • Rosario Cammarota, Matthias Schunter, Anand Rajan, Fabian Boemer, Ágnes Kiss, Amos Treiber, Christian Weinert, Thomas Schneider, Emmanuel Stapf, Ahmad-Reza Sadeghi, Daniel Demmler, Joshua Stock, Huili Chen, Siam Umar Hussain, Sadegh Riazi, Farinaz Koushanfar, Saransh Gupta, Tajan Simunic Rosing, Kamalika Chaudhuri, Hamid Nejatollahi, Nikil Dutt, Mohsen Imani, Kim Laine, Anuj Dubey, Aydin Aysu, Fateme Sadat Hosseini, Chengmo Yang, Eric Wallace, Pamela Norton
Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time.
no code implementations • 14 May 2020 • Behnam Khaleghi, Mohsen Imani, Tajana Rosing
In this paper, we target privacy-preserving training and inference of brain-inspired Hyperdimensional (HD) computing, a new learning algorithm that is gaining traction due to its light-weight computation and robustness particularly appealing for edge devices with tight constraints.
no code implementations • 27 Nov 2019 • Samuel Bosch, Alexander Sanchez de la Cerda, Mohsen Imani, Tajana Simunic Rosing, Giovanni De Micheli
It is a promising solution for achieving high energy efficiency in different machine learning tasks, such as classification, semi-supervised learning, and clustering.
1 code implementation • 18 Feb 2019 • Mohsen Imani, Mohammad Saidur Rahman, Nate Mathews, Matthew Wright
Since the attacker gets to design his classifier based on the defense design, we first demonstrate that at least one technique for generating adversarial-example based traces fails to protect against an attacker using adversarial training for robust classification.
Website Fingerprinting Defense
Cryptography and Security
no code implementations • 15 Jun 2018 • Mohsen Imani, Mohammad Samragh, Yeseong Kim, Saransh Gupta, Farinaz Koushanfar, Tajana Rosing
To enable in-memory processing, RAPIDNN reinterprets a DNN model and maps it into a specialized accelerator, which is designed using non-volatile memory blocks that model four fundamental DNN operations, i. e., multiplication, addition, activation functions, and pooling.
1 code implementation • 26 Aug 2016 • Mohsen Imani, Mehrdad Amirabadi, Matthew Wright
In this paper, we examine both the process of selecting among pre-built circuits and the process of selecting the path of relays for use in building new circuits to improve performance while maintaining anonymity.
Cryptography and Security