Quantizing YOLOv7: A Comprehensive Study

• URL: http://arxiv.org/abs/2407.04943v1
• Date: Sat, 6 Jul 2024 03:23:04 GMT
• Title: Quantizing YOLOv7: A Comprehensive Study
• Authors: Mohammadamin Baghbanbashi, Mohsen Raji, Behnam Ghavami,
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: YOLO is a deep neural network (DNN) model presented for robust real-time object detection following the one-stage inference approach. It outperforms other real-time object detectors in terms of speed and accuracy by a wide margin. Nevertheless, since YOLO is developed upon a DNN backbone with numerous parameters, it will cause excessive memory load, thereby deploying it on memory-constrained devices is a severe challenge in practice. To overcome this limitation, model compression techniques, such as quantizing parameters to lower-precision values, can be adopted. As the most recent version of YOLO, YOLOv7 achieves such state-of-the-art performance in speed and accuracy in the range of 5 FPS to 160 FPS that it surpasses all former versions of YOLO and other existing models in this regard. So far, the robustness of several quantization schemes has been evaluated on older versions of YOLO. These methods may not necessarily yield similar results for YOLOv7 as it utilizes a different architecture. In this paper, we conduct in-depth research on the effectiveness of a variety of quantization schemes on the pre-trained weights of the state-of-the-art YOLOv7 model. Experimental results demonstrate 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, respectively, with only 2.5% and 1% accuracy loss compared to the full-precision baseline model.

Related papers

• Evaluating the Evolution of YOLO (You Only Look Once) Models: A Comprehensive Benchmark Study of YOLO11 and Its Predecessors [0.0]
  This study presents a benchmark analysis of various YOLO (You Only Look Once) algorithms, from YOLOv3 to the newest addition, YOLO11. It evaluates their performance on three diverse datasets: Traffic Signs (with varying object sizes), African Wildlife (with diverse aspect ratios and at least one instance of the object per image), and Ships and Vessels (with small-sized objects of a single class)
  arXiv  Detail & Related papers  (2024-10-31T20:45:00Z)
• YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision [0.6662800021628277]
  This paper focuses on the evolution of the YOLO (You Only Look Once) object detection algorithm, focusing on YOLOv5, YOLOv8, and YOLOv10. We analyze the architectural advancements, performance improvements, and suitability for edge deployment across these versions.
  arXiv  Detail & Related papers  (2024-07-03T10:40:20Z)
• 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)
• 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)
• 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)
• YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems [0.0873811641236639]
  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
  arXiv  Detail & Related papers  (2023-07-26T01:51:10Z)
• Model Compression Methods for YOLOv5: A Review [1.2387676601792899]
  We focus on pruning and quantization due to their comparative modularity. This is the first specific review paper that surveys pruning and quantization methods from an implementation point of view on YOLOv5. Our study is also extendable to newer versions of YOLO as implementing them on resource-limited devices poses the same challenges that persist even today.
  arXiv  Detail & Related papers  (2023-07-21T21:07:56Z)
• Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras [62.70541164894224]
  We introduce several architecture choices which allow us to scale the depth and complexity of such models while maintaining low computation. Our method runs 3.7 times faster than a dense graph neural network, taking only 8.4 ms per forward pass.
  arXiv  Detail & Related papers  (2022-11-22T15:14:20Z)
• 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)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)

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.