Search Results for author: Mohsen Imani

Found 40 papers, 4 papers with code

Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?

no code implementations27 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.

Anomaly Detection

Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Tracking

no code implementations17 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.

Decoder Referring Multi-Object Tracking

Expanding Event Modality Applications through a Robust CLIP-Based Encoder

no code implementations4 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.

Few-Shot Learning Object Recognition +1

Exploiting Boosting in Hyperdimensional Computing for Enhanced Reliability in Healthcare

no code implementations21 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.

Continuous GNN-based Anomaly Detection on Edge using Efficient Adaptive Knowledge Graph Learning

no code implementations13 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.

Anomaly Detection Edge-computing +3

Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing

no code implementations2 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

PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation

no code implementations30 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.

Anomaly Detection Descriptive +4

A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI

no code implementations20 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.

VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation

1 code implementation13 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.

Decoder Language Modelling +2

Promoting Fairness in Link Prediction with Graph Enhancement

no code implementations13 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.

Fairness Link Prediction

Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach

no code implementations1 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.

Pose Estimation

Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces

no code implementations13 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.

Attribute Language Modeling +5

Explainable Differential Privacy-Hyperdimensional Computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring

no code implementations9 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.

Anomaly Detection Defect Detection

MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation

no code implementations27 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.

Anomaly Detection Graph Generation +7

Hyperdimensional Quantum Factorization

no code implementations13 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.

Information Retrieval Retrieval

Generalized Holographic Reduced Representations

no code implementations15 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.

Memorization

NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval

no code implementations17 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.

Image Retrieval Retrieval

Self-Attention Based Semantic Decomposition in Vector Symbolic Architectures

no code implementations20 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.

Interpretable Machine Learning

TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection

no code implementations12 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.

Language Modeling Language Modelling +4

HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning

no code implementations9 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.

Graph Classification Graph Learning +1

HEAL: Brain-inspired Hyperdimensional Efficient Active Learning

no code implementations17 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).

Active Learning Diversity

A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmission

no code implementations3 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.

HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing

no code implementations4 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.

object-detection Object Detection

HDQMF: Holographic Feature Decomposition Using Quantum Algorithms

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.

Towards Efficient Hyperdimensional Computing Using Photonics

no code implementations29 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).

Learning from Hypervectors: A Survey on Hypervector Encoding

no code implementations1 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.

Survey

DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification

1 code implementation11 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.

Efficient Personalized Learning for Wearable Health Applications using HyperDimensional Computing

no code implementations1 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.

BIG-bench Machine Learning Privacy Preserving

Efficient Off-Policy Reinforcement Learning via Brain-Inspired Computing

no code implementations14 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.

Decision Making Q-Learning +3

Spiking Hyperdimensional Network: Neuromorphic Models Integrated with Memory-Inspired Framework

no code implementations1 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.

Prive-HD: Privacy-Preserved Hyperdimensional Computing

no code implementations14 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.

Privacy Preserving Quantization

QubitHD: A Stochastic Acceleration Method for HD Computing-Based Machine Learning

no code implementations27 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.

BIG-bench Machine Learning Classification +2

Mockingbird: Defending Against Deep-Learning-Based Website Fingerprinting Attacks with Adversarial Traces

1 code implementation18 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

RAPIDNN: In-Memory Deep Neural Network Acceleration Framework

no code implementations15 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.

Clustering speech-recognition +3

Modified Relay Selection and Circuit Selection for Faster Tor

1 code implementation26 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

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