mlsanityData to 14 Oct 2026

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

arXiv 2307.11962 ↗First posted 22 Jul 2023cs.RO cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 73 references that are in the map. First posted on arXiv 22 Jul 2023.

Builds on

33 of 73 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  8. 2017Graph Attention Networkscited by 8,923
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  10. 2017Inductive Representation Learning on Large Graphscited by 6,320
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  12. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
21 more
  1. 2022A Generalist Agentcited by 808
  2. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  3. 2019Importance Estimation for Neural Network Pruningcited by 541
  4. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 511
  5. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  6. 2017Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeoncited by 221
  7. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  8. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 101
  9. 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
  10. 2018Compressing Neural Networks using the Variational Information Bottleneckcited by 59
  11. 2018DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systemscited by 50
  12. 2022A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Predictioncited by 48
  13. 2022Uncertainty Quantification of Collaborative Detection for Self-Drivingcited by 46
  14. 2022Graph Neural Networks in IoT: A Surveycited by 28
  15. 2018Multi-Task Zipping via Layer-wise Neuron Sharingcited by 20
  16. 2022Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligencecited by 16
  17. 2019Embodied Multimodal Multitask Learningcited by 13
  18. 2020AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobilescited by 10
  19. 2018Unifying and Merging Well-trained Deep Neural Networks for Inference Stagecited by 8
  20. 2019Neural Autonomous Navigation with Riemannian Motion Policycited by 6
  21. 2019Pruning-Aware Merging for Efficient Multitask Inferencecited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2023RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamicscited by 6
  2. 2023R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Roboticscited by 5
  3. 2026TetraRL: A Self-Adaptive Runtime for On-Device Deep Reinforcement Learning Systemscited by 0