paper-with-me

Papers

MIMONet: Multi-Input Multi-Output On-Device Deep Learning

2023-07-22 · Zexin Li, Xiaoxi He, Yufei Li, Wei Yang, Lothar Thiele, Cong Liu

Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that multi-input single-output (MISO) deep neural networks (DNN) outperform traditional single-input single-output (SISO) models, representing a significant step towards this goal. In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage. Leveraging existing SISO model compression techniques, MIMONet develops a new deep-compression method that is specifically tailored to MIMO models. This new method explores unique yet non-trivial properties of the MIMO model, resulting in boosted accuracy and on-device efficiency. Extensive experiments on three embedded platforms commonly used in robotic systems, as well as a case study using the TurtleBot3 robot, demonstrate that MIMONet achieves higher accuracy and superior on-device efficiency compared to state-of-the-art SISO and MISO models, as well as a baseline MIMO model we constructed. Our evaluation highlights the real-world applicability of MIMONet and its potential to significantly enhance the performance of intelligent robotic systems.

📄 PDF Abstract BibTeX arXiv:2307.11962

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningModel Compression

Similar Papers 제목 키워드 기반

MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition

2023-12-05 · NeurIPS 2023 11 · Nicolas Menet, Michael Hersche, Geethan Karunaratne, Luca Benini 외

With the advent of deep learning, progressively larger neural networks have been designed to solve complex tasks. We take advantage of these capacity-rich models to lower the cost of inference by exploiting computation i…

MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object Detection

2026-08-26 · Zhaojian Yao, Wei Gao, Tiesong Zhao, Hui Yuan 외 arxiv

The existing methods for saliency detection task focus on the application of multi-level features, aiming to take advantage of the respective strengths of high- and low-level features. However, because the inputs of thes…

Salient Object DetectionSaliency Detection

RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics

2023-08-29 · Zexin Li, Tao Ren, Xiaoxi He, Cong Liu

Intelligent robots are designed to effectively navigate dynamic and unpredictable environments laden with moving mechanical elements and objects. Such environment-induced dynamics, including moving obstacles, can readily…

NavigateScheduling

RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics

2026-05-21 · Zexin Li, Tao Ren, Johnathan Liu, Xiaoxi He 외 arxiv

Robots deployed in dynamic environments must contend with environment-driven changes that reshape computation at runtime: new tasks may appear, precedence relations can shift, and overall workload structure evolves, all …

Random Access with Massive MIMO-OTFS in LEO Satellite Communications

2022-02-26 · Boxiao Shen, Yongpeng Wu, Jianping An, Chengwen Xing 외

This paper considers the joint channel estimation and device activity detection in the grant-free random access systems, where a large number of Internet-of-Things devices intend to communicate with a low-earth orbit sat…

Action DetectionActivity Detection