CoChat

Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors

Open access
Kim, Sungrae, Kim, Hyun · 2021 · IEEE Access

The DOI matches its Crossref record; 49 of the 63 references it cites were found in a registry or an index, and 1 are not checked yet; 13 of the 27 sources its claims cite were checked for support.

Abstract

In the field of object detection, deep learning has greatly improved accuracy compared to previous algorithms and has been used widely in recent years. However, object detection using deep learning requires many hardware (HW) resources due to the huge computations for high performance, making it very difficult to run real-time on embedded platforms. Therefore, various compression methods have been studied to solve this problem. In particular, quantization methods greatly reduce the computational burden of deep learning by reducing the number of bits used for weights and activation functions in deep learning. However, most of these existing studies targeted only object classification and cannot be applied to object detection. Furthermore, most of the existing quantization studies are based on floating-point operations, which requires additional effort when implementing HW accelerators. This paper proposes an HW-friendly fixed-point-based quantization method that can also be applied to object detection. In the proposed method, the center of the weight distribution is adjusted to zero by subtracting the mean of weight parameters before quantization, and the retraining process is iteratively applied to minimize the accuracy drop caused by quantization. Furthermore, while applying the proposed method to object detection, performance degradation is minimized by considering the minimum and maximum values of weight parameters of deep learning networks. When applying the proposed quantization method to representative one-stage object detectors, You Only Look Once v3 and v4 (YOLOv3 and YOLOv4), detection accuracy similar to the original networks (i.e., YOLOv3 and YOLOv4) with a single-precision floating-point format (32-bit) is maintained despite expressing weights with only about 20% of the bits compared to a single-precision floating-point format in COCO dataset.

Verified 2026-11-19 · 1 reference not checked yet

Overview

CoChat Summary

## TL;DR

The paper proposes an HW-friendly fixed-point quantization method for deep CNNs that combines zero-centering of weights and iterative retraining, and extends it to object detectors with layer-wise bit allocation. On COCO, it reports near-original mAP for YOLOv3 and YOLOv4 while using only about 20% of the original weight bits.

## Key findings

  • On CIFAR-10 with VGG-7, applying both zero-centered quantization and iterative retraining reduced accuracy drop to 0.1% at 4/4 bits; the paper reports 91.97% accuracy versus 92.07% for the original network.
  • On YOLOv3 with COCO, the proposed method achieved 54.52 mAP at 6.58 average weight bits, compared with 54.64 mAP and 32 bits for the original model; the basic 8-bit quantized model was 52.60 mAP, while the proposed 8-bit model was 54.52 mAP.
  • On YOLOv4 with COCO, the proposed method achieved 62.9 mAP at 8 bits versus 64.17 mAP for the original; with bit allocation, it reached 63.54 mAP at 5.99 average weight bits.
  • The paper reports that iterative retraining reduced the portion of ambiguous weights from 23.33% to 8.73% in VGG-7, 22.95% to 18.01% in YOLOv3, and 20.06% to 14.65% in YOLOv4.

## Methods

  • Proposed a fixed-point quantization scheme that subtracts the mean of layer weights to center them around zero, then quantizes and retrains iteratively while gradually increasing the quantization rate.
  • Evaluated on CIFAR-10 with VGG-7 for image classification and COCO with YOLOv3/YOLOv4 for object detection; experiments were run on a Linux server with a GeForce RTX 2080Ti.
  • For object detection, added a layer-wise bit allocation strategy using grid search to choose per-layer weight bitwidths that maximize mAP.

## Limitations

  • The paper states that basic quantization without the proposed zero-centered and iterative retraining techniques causes severe performance degradation on object detection, even at 8 bits.
  • The text makes evident that the method still has noticeable mAP loss at lower bitwidths for object detection: for example, YOLOv3 drops to 50.05 mAP at 6 bits, 46.95 at 5 bits, and 42.02 at 4 bits even with the proposed method.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/access.2021.3054879

Cites

49 of 50 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

FIGURE 1 Representation of floating-point and fixed-point numbers.
FIGURE 1 Representation of floating-point and fixed-point numbers.From the PDF
FIGURE 2 Distribution of the number of weights. (a) Normal ( i.e. , Pre-trained) weights. (b) m -bit quantized weights based on floating-point representation. (c) m -bit quantized weights based on fixed-point representation.
FIGURE 2 Distribution of the number of weights. (a) Normal ( i.e. , Pre-trained) weights. (b) m -bit quantized weights based on floating-point representation. (c) m -bit quantized weights based on fixed-point representation.From the PDF
FIGURE 3 The network architecture. (a) YOLOv3. (b) YOLOv4.
FIGURE 3 The network architecture. (a) YOLOv3. (b) YOLOv4.From the PDF
FIGURE 4 Flowchart of the proposed quantization.
FIGURE 4 Flowchart of the proposed quantization.From the PDF
FIGURE 5 The median of maximum weights and minimum weights. (a) VGG-7 in Cifar10 dataset. (b) YOLOv3 in COCO dataset. (c) YOLOv4 in COCO dataset.
FIGURE 5 The median of maximum weights and minimum weights. (a) VGG-7 in Cifar10 dataset. (b) YOLOv3 in COCO dataset. (c) YOLOv4 in COCO dataset.From the PDF
FIGURE 6 Flow of CONV arithmetic operation. (a) Original method. (b) Proposed method.
FIGURE 6 Flow of CONV arithmetic operation. (a) Original method. (b) Proposed method.From the PDF
FIGURE 7 Distribution of weight parameters according to each quantization rate.
FIGURE 7 Distribution of weight parameters according to each quantization rate.From the PDF
Image 8
From the PDF
FIGURE 8 Number of bits used in each convolutional layer. (a) YOLOv3. (b) YOLOv4.
FIGURE 8 Number of bits used in each convolutional layer. (a) YOLOv3. (b) YOLOv4.From the PDF
TABLE 6. mAP Comparison results on each network in COCO dataset.
TABLE 6. mAP Comparison results on each network in COCO dataset.From the PDF
Image 11
From the PDF
Image 12
From the PDF
Image 13
From the PDF
Image 14
From the PDF
Image 15
From the PDF
Image 16
From the PDF
Image 17
From the PDF

Verification

Claims the paper makes

5 Valid · 3 Not valid · 11 Not checked · 60 Own results and interpretations

30 more claims

Create a free account to see all 79 claims and to verify the 9 references still open.

See all claims — free account
  • It may state two separate claims as one. 37
  • The quote only partly states this claim. 4
  • Probably not a substantial claim. 11

Create a free account to see these claims.

Citations

Cites

Show all 50 references

Cited by

See all 71

Metadata

Authors
Kim, S., & Kim, H.
Affiliations
Seoul National University of Science and Technology (KR)
Venue
IEEE Access
Published
2021
Volume
9
Pages
20828-20839
ISSN
2169-3536 (ISSN-L)
OpenAlex
W3122390253
Cited by
71
References
63
Citations by year
2026: 3 · 2025: 8 · 2024: 22 · 2023: 11 · 2022: 15 · 2021: 11
FWCI
4.52
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Institute of Information & Communications Technology Planning & Evaluation (IITP) Grant funded by the Korean Government (MSIT) (2020-0-01305)
  • Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2019R1A6A1A03032119)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Numerical Methods and Algorithms
Keywords
fixed-point quantization, object detection, model compression, YOLOv3, YOLOv4, weight distribution, embedded hardware acceleration, low-bit precision, accuracy degradation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors. https://app.cochat.ai/papers/10.1109/access.2021.3054879
The paper
Kim, S., & Kim, H. (2021). Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors. IEEE Access. https://doi.org/10.1109/access.2021.3054879

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.