Computer Science

Computer Science ›› 2025, Vol. 52 ›› Issue (11A): 241100059-7.doi: 10.11896/jsjkx.241100059

• Artificial Intelligence • Previous Articles     Next Articles

Balanced Quantization Strategy for Efficient Post-training Quantization of BEVFormer

ZHANG Xiaoxuan, TANG Xiaoyong   

  1. School of Computer and Communications Engineering,Changsha University of Science & Technology,Changsha 410114,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    National Natural Science Foundation of China(6197214)．

PDF (PC)

8

Abstract: BEVFormer’s bird’s-eye view(BEV) representation achieves strong results in autonomous driving applications.However,its high memory use and computational demands make real-time deployment difficult on resource-constrained devices.BEVFormer’s ReLU activation values vary widely,creating an uneven distribution that traditional quantization metrics,such as cosine similarity and mean square error(MSE),struggle to address effectively.To overcome these limitations,this paper introduces a new post-training quantization(PTQ) method,the Balanced Quantization Strategy.This method is specifically optimized for BEVFormer,focusing on quantizing linear layers and ReLU activations.For linear layers,it uses predefined quantization ranges,while ReLU activations are quantized with customized ranges to retain key value accuracy.Further,Hessian matrix optimization dyna-mically adjusts scaling factors,reducing quantization errors and stabilizing the quantization process.Results show that the Balanced Quan-tization Strategy improves computational efficiency with minimal accuracy loss.In testing on the nuScenes dataset,the proposed 8-bit quantization method achieves less than a 1% drop in NDS,maintaining BEVFormer’s high performance.

Key words: BEVFormer, ReLU activation, Outputs of the linear layers, Balanced Quantization Strategy, Hessian matrix

CLC Number: 

  • TP391
[1]HUANG D Q,HUANG H F,HUANG D Y,et al.A Survey on BEV Perception Learning in Autonomous Driving [J/OL].Computer Engineering and Applications,1-23 [2024-11-06].http://kns.cnki.net/kcms/detail/11.2127.TP.20241031.1529.016.html.
[2]MA Y X,WANG T,BAI X Y,et al.Vision-Centric BEV Perception:A Survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(12):10978-10997.
[3]LI Z,WANG W,LI H,et al.Bevformer:Learning bird’s-eye-view representation from multi-camera images via spatiotemporal transformers[C]//European Conference on Computer Vision.Cham:Springer,2022:1-18.
[4]YANG C,CHEN Y,TIAN H,et al.Bevformer v2:Adaptingmodern image back-bones to bird’s-eye-view recognition via perspective supervi-sion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2023:17830-17839.
[5]MA Y,WANG T,BAI X,et al.Vision-centric bev perception:A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(12):10978-10996.
[6]LIU Z,TANG H,AMINI A,et al.Bevfusion:Multi-task multi-sensor fusion with unified bird’s-eye view representation[C]//2023 IEEE Inter-national Conference on Robotics and Automation(ICRA).IEEE,2023:2774-2781.
[7]WANG C,WANG Z,XU X,et al.Towards Accurate Post-training Quantization for Diffusion Models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2024.
[8]DIAO H,LI G,XU S,et al.Attention Round for Post-Training Quantization[J].Neurocomputing,2022,521:364-373.
[9]BANNER R,NAHSHAN Y,SOUDRY D.Post training 4-bit quantization of convolutional networks for rap-id-deployment[C]//Advances in Neural Information Processing Systems.2019:1-12.
[10]CHOUKROUN Y,KRAVCHIK E,YANG F,et al.Low-bitquantization of neural networks for efficient inference[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop(ICCVW).2019:1-12.
[11]CHENG Y,WANG D,ZHOU P,et al.A Survey of Model Compression and Acceleration for Deep Neural Networks[J].arXiv:1710.09282,2017.
[12]YAO Z,AMINABADI R Y,ZHANG M,et al.ZeroQuant:Efficient and Affordable Post-Training Quantization for Large-Scale Transformers[C]//Advances in Neural Information Processing Systems 35(NeurIPS 2022).2022:27168-27183.
[13]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Advances in Neural Information Processing Systems.2017.
[14]LIU Z,WANG Y,HAN K,et al.Post-training quantization for vision transformer[C]//Advances in Neural Information Processing Systems.2021:28092-28103.
[15]YUAN Z,XUE C,CHEN Y,et al.PTQ4ViT:Post-trainingQuantization for Vision Transformers with Twin Uniform Quantization[C]//2021 European Conference on Computer Vision(ECCV).2021:1-12.
[16]JIAO J,JIE Z,CHEN S,et al.MSMDFusion:Multi-Depth Seed Based Fusion of LiDAR and Camera Data for Enhanced 3D Object Detection[J].IEEE Transactions on Intelligent Transportation Systems,2023,25:1-12.
[17]YIN Z,ZHOU X,KRÄHENBÜHL P.Multimodal Virtual Point 3D Detection:Establishing Fine-Grained Feature Alignment Across Different Modalities[C]//Proceedings of the IEEE International Conference on Computer Vision(ICCV).2021:1-12.
[18]BAI H,HU Z,HUANG Q,et al.TransFusion:A Robust Li-DAR-Camera Fusion Method for 3D Object Detection Using Transformers[J].IEEE Transactions on Intelligent Transportation Systems,2022,25:1-12.
[19]CHEN L.Dense Projection Fusion(DPFusion):A Multi-Stage,Fine-Grained Fusion Technique for 3D Object Detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46:35-56.
[20]DOE J.Piecewise Linear Quantization(PWLQ)[J].Neural Networks,2024,58(C):123-145.
[21]NAGEL J,LEUNG T,SCHMIDT T,Casale P.AdaRound:Adaptive rounding for post-training quantization[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2020:1-12.
[22]LI B,CHEN Q,XU H,et al.BRECQ:Bit-reconstruction quantization for ultra low-bit quantization aware training[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2021:1-12.
[23]HUBARA I,COURBARIAUX M,SOUDRY D,et al.Block-Wise Mixed-Precision Quantization:Enabling High Efficiency for Practical ReRAM-based DNN Accelerators[J].IEEE Transactions on Circuits and Systems I:Regular Papers,2021,68(11):1-12.
[24]BONDARENKO Y,NAGEL M,BLANKEVOORT T.Under-standing and Overcoming the Challenges of Efficient Transformer Quantization[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:7947-7969.
[25]FRANTAR M,HUBARA I,SOUDRY D,et al.CompressingDeep Neural Networks by Combining Weight Pruning with Post-Training Quantization[C]//Proceedings of the 36th Inernational Conference on Neural Information Processing Systems.2022:12760-12773.
[26]XIAO G,LIN J,SEZNEC M,et al.SmoothQuant:Accurate and Efficient Post-Training Quantization for Large Language Models[C]//40th International Conference on Machine Learning(ICML).2023:10-12.
[1] XU Zhen-chi, JI Lei, LIU Xiao-rong and ZHOU Xiao-jia. Recognition of Impurities Based on their Distinguishing Feature in Mushrooms [J]. Computer Science, 2015, 42(Z11): 203-205.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.