TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers

• URL: http://arxiv.org/abs/2306.00001v2
• Date: Wed, 12 Jul 2023 06:10:52 GMT
• Title: TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers
• Abstract summary: This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5MB memory available for storing convolutional neural network weights.
• Score: 1.2846479438896337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180fps and an ultra-low energy consumption of only 196{\mu}J per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper.

Related papers

• TinyML Enhances CubeSat Mission Capabilities [8.462623779881566]
  The paper presents a Convolutional Neural Networks (ConvNets) model optimization and deployment pipeline for onboard image classification.<n>Our pipeline integrates structured iterative pruning, post-training INT8 quantization, and hardware-aware operator mapping to compress models.<n>We demonstrate an average reduction in RAM usage of 89.55% and Flash memory of 709% for the optimized models.
  arXiv  Detail & Related papers  (2026-03-20T17:51:07Z)
• TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings [0.14504054468850666]
  We present TinyVLM, the first framework enabling zero-shot object detection on resource-constrained MCUs with less than 1MB of memory.<n>TinyVLM achieves competitive zero-shot accuracy on COCO, Flowers102, and Food101 while requiring only 285KB of RAM and 892KB of flash memory.
  arXiv  Detail & Related papers  (2026-02-24T05:32:51Z)
• DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units [1.4447019135112429]
  This paper proposes an adaptive tiling method for lightweight and energy-efficient object detection networks, including YOLO-based models and the popular FOMO network. The proposed tiling enables object detection on low-power MCUs with no compromise on accuracy compared to large-scale detection models.
  arXiv  Detail & Related papers  (2024-10-22T07:37:47Z)
• An Ultra-low Power TinyML System for Real-time Visual Processing at Edge [7.327401565768275]
  This brief presents an extremely tiny backbone to construct high efficiency CNN models for various visual tasks. A specially designed neural co-processor (NCP) is interconnected with MCU to build an ultra-low power TinyML system. The proposed TinyML system based on our model, NCP and instruction set yields considerable accuracy and achieves a record ultra-low power of 160mW.
  arXiv  Detail & Related papers  (2022-07-11T06:56:27Z)
• Sparse Compressed Spiking Neural Network Accelerator for Object Detection [0.1246030133914898]
  Spiking neural networks (SNNs) are inspired by the human brain and transmit binary spikes and highly sparse activation maps. This paper proposes a sparse compressed spiking neural network accelerator that takes advantage of the high sparsity of activation maps and weights. The experimental result of the neural network shows 71.5$%$ mAP with mixed (1,3) time steps on the IVS 3cls dataset.
  arXiv  Detail & Related papers  (2022-05-02T09:56:55Z)
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning [72.80896338009579]
  We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs. We propose a generic patch-by-patch inference scheduling, which significantly cuts down the peak memory. We automate the process with neural architecture search to jointly optimize the neural architecture and inference scheduling, leading to MCUNetV2.
  arXiv  Detail & Related papers  (2021-10-28T17:58:45Z)
• NAS-FCOS: Efficient Search for Object Detection Architectures [113.47766862146389]
  We propose an efficient method to obtain better object detectors by searching for the feature pyramid network (FPN) and the prediction head of a simple anchor-free object detector. With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs.
  arXiv  Detail & Related papers  (2021-10-24T12:20:04Z)
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays [66.62377866022221]
  Latent Replay-based Continual Learning (CL) techniques enable online, serverless adaptation in principle. We introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power processor. Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory.
  arXiv  Detail & Related papers  (2021-10-20T11:01:23Z)
• GnetDet: Object Detection Optimized on a 224mW CNN Accelerator Chip at the Speed of 106FPS [10.644839299403612]
  We optimize the object detection model on a CNN accelerator chip by minimizing the CPU load. The experimental result shows that the GnetDet model running on a 224mW chip achieves the speed of 106FPS with excellent accuracy.
  arXiv  Detail & Related papers  (2021-02-19T06:16:42Z)
• Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices [20.349809458335532]
  Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on Deep Neural Networks are very effective, but highly demanding in terms of memory, power, and throughput. In this paper, we explore the combination of extreme quantization to a small-print binary neural network (BNN) with the highly energy-efficient, RISC-V-based (8+1)-core GAP8 microcontroller.
  arXiv  Detail & Related papers  (2021-01-12T12:38:23Z)
• Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers [76.30674794049293]
  This paper presents an automated mixed-precision quantization flow based on the HAQ framework but tailored for the memory and computational characteristics of MCU devices. Specifically, a Reinforcement Learning agent searches for the best uniform quantization levels, among 2, 4, 8 bits, of individual weight and activation tensors. Given an MCU-class memory bound to 2MB for weight-only quantization, the compressed models produced by the mixed-precision engine result as accurate as the state-of-the-art solutions.
  arXiv  Detail & Related papers  (2020-08-12T06:09:58Z)
• Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection [99.94079901071163]
  This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs) We target applications where multiple sensors transmit data to a local processing unit, which executes a detection algorithm. Our detector is able to perform a detection every 450 ms, with an overall testing F1 score of 83%.
  arXiv  Detail & Related papers  (2020-04-03T17:36:26Z)
• NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection [170.30694322460045]
  We propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features. A single-shot network called NETNet is constructed for scale-aware object detection.
  arXiv  Detail & Related papers  (2020-01-18T15:21:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.