YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems

• URL: http://arxiv.org/abs/2307.13901v2
• Date: Mon, 21 Aug 2023 17:55:07 GMT
• Title: YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems
• Authors: Ivan Lazarevich and Matteo Grimaldi and Ravish Kumar and Saptarshi Mitra and Shahrukh Khan and Sudhakar Sah
• Abstract summary: We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms. We collect accuracy and latency numbers for a variety of YOLO-based one-stage detectors at different model scales by performing a fair, controlled comparison of these detectors with a fixed training environment. We evaluate training-free accuracy estimators used in neural architecture search on YOLOBench and demonstrate that, while most state-of-the-art zero-cost accuracy estimators are outperformed by a simple baseline like MAC count, some of them can be effectively used to
• Score: 0.0873811641236639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms (x86 CPU, ARM CPU, Nvidia GPU, NPU). We collect accuracy and latency numbers for a variety of YOLO-based one-stage detectors at different model scales by performing a fair, controlled comparison of these detectors with a fixed training environment (code and training hyperparameters). Pareto-optimality analysis of the collected data reveals that, if modern detection heads and training techniques are incorporated into the learning process, multiple architectures of the YOLO series achieve a good accuracy-latency trade-off, including older models like YOLOv3 and YOLOv4. We also evaluate training-free accuracy estimators used in neural architecture search on YOLOBench and demonstrate that, while most state-of-the-art zero-cost accuracy estimators are outperformed by a simple baseline like MAC count, some of them can be effectively used to predict Pareto-optimal detection models. We showcase that by using a zero-cost proxy to identify a YOLO architecture competitive against a state-of-the-art YOLOv8 model on a Raspberry Pi 4 CPU. The code and data are available at https://github.com/Deeplite/deeplite-torch-zoo

Related papers

• MCUBench: A Benchmark of Tiny Object Detectors on MCUs [36.77761421733794]
  MCUBench is a benchmark featuring over 100 YOLO-based object detection models evaluated on the VOC dataset across seven different MCUs. This benchmark provides detailed data on average precision, latency, RAM, and Flash usage for various input resolutions and YOLO-based one-stage detectors.
  arXiv  Detail & Related papers  (2024-09-27T16:02:56Z)
• Quantizing YOLOv7: A Comprehensive Study [0.0]
  This paper studies the effectiveness of a variety of quantization schemes on the pre-trained weights of the state-of-the-art YOLOv7 model. Results show that using 4-bit quantization coupled with the combination of different granularities results in 3.92x and 3.86x memory-saving for uniform and non-uniform quantization.
  arXiv  Detail & Related papers  (2024-07-06T03:23:04Z)
• YOLOv10: Real-Time End-to-End Object Detection [68.28699631793967]
  YOLOs have emerged as the predominant paradigm in the field of real-time object detection. The reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs. We introduce the holistic efficiency-accuracy driven model design strategy for YOLOs.
  arXiv  Detail & Related papers  (2024-05-23T11:44:29Z)
• MODIPHY: Multimodal Obscured Detection for IoT using PHantom Convolution-Enabled Faster YOLO [10.183459286746196]
  We introduce YOLO Phantom, one of the smallest YOLO models ever conceived. YOLO Phantom achieves comparable accuracy to the latest YOLOv8n model while simultaneously reducing both parameters and model size. Its real-world efficacy is demonstrated on an IoT platform with advanced low-light and RGB cameras, seamlessly connecting to an AWS-based notification endpoint.
  arXiv  Detail & Related papers  (2024-02-12T18:56:53Z)
• YOLO-World: Real-Time Open-Vocabulary Object Detection [87.08732047660058]
  We introduce YOLO-World, an innovative approach that enhances YOLO with open-vocabulary detection capabilities. Our method excels in detecting a wide range of objects in a zero-shot manner with high efficiency. YOLO-World achieves 35.4 AP with 52.0 FPS on V100, which outperforms many state-of-the-art methods in terms of both accuracy and speed.
  arXiv  Detail & Related papers  (2024-01-30T18:59:38Z)
• Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism [40.31805155724484]
  New designed model named as Gold-YOLO, which boosts the multi-scale feature fusion capabilities. We implement MAE-style pretraining in the YOLO-series for the first time, allowing YOLOseries models could be to benefit from unsupervised pretraining.
  arXiv  Detail & Related papers  (2023-09-20T14:03:47Z)
• YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection [80.11152626362109]
  We provide an efficient and performant object detector, termed YOLO-MS. We train our YOLO-MS on the MS COCO dataset from scratch without relying on any other large-scale datasets. Our work can also be used as a plug-and-play module for other YOLO models.
  arXiv  Detail & Related papers  (2023-08-10T10:12:27Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors [68.8204255655161]
  This paper compares four state-of-the-art algorithms in two real applications: gesture recognition based on accelerometer data and image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs.
  arXiv  Detail & Related papers  (2022-09-01T17:05:20Z)
• A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery [94.78943497436492]
  We present YOLO-S, a simple, fast and efficient network for small target detection. YOLO-S exploits a small feature extractor based on Darknet20, as well as skip connection, via both bypass and concatenation. YOLO-S has an 87% decrease of parameter size and almost one half FLOPs of YOLOv3, making practical the deployment for low-power industrial applications.
  arXiv  Detail & Related papers  (2022-04-05T16:29:49Z)

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.