Anti-interference diffractive deep neural networks for multi-object recognition

Zhiqi Huang; Yufei Liu; Nan Zhang; Zian Zhang; Qiming Liao; Cong He; Shendong Liu; Youhai Liu; Hongtao Wang; Xingdu Qiao; Joel K. W. Yang; Yan Zhang; Lingling Huang; Yongtian Wang

doi:10.1038/s41377-026-02188-7

Your Location：

Home >

Browse articles >

Anti-interference diffractive deep neural networks for multi-object recognition

Original Articles

- Anti-interference diffractive deep neural networks for multi-object recognition
- Light: Science & Applications Vol. 15, Issue 4, Pages: 1172-1181(2026)
- Affiliations：
  
  1.Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China
  2.National Key Laboratory on Near-surface Detection, Beijing 100072, China
  3.Beijing Key Laboratory of Metamaterials and Devices, Key Laboratory of Terahertz Optoelectronics of Ministry of Education, Capital Normal University, Department of Physics, Capital Normal University, Beijing 100048, China
  4.Qiyuan Lab, Beijing 100095, China
  5.Engineering Product Development, Singapore University of Technology and Design, Singapore 487372, Singapore
  6.Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA 19104, USA
- Author bio：
  
  Nan Zhang (nanzhang@bit.edu.cn)
  Yan Zhang (yzhang@cnu.edu.cn)
  Lingling Huang (huanglingling@bit.edu.cn)
- Funds：
- DOI：10.1038/s41377-026-02188-7
  CLC：
- Received：18 August 2025，
  
  Revised：2025-12-18，
  
  Accepted：09 January 2026，
  
  Online First：03 February 2026，
  
  Published：30 April 2026
- Accepted：
Scan QR Code
Huang, Z. Q. et al. Anti-interference diffractive deep neural networks for multi-object recognition. Light: Science & Applications, 15, 1172-1181 (2026).
DOI：

Huang, Z. Q. et al. Anti-interference diffractive deep neural networks for multi-object recognition. Light: Science & Applications, 15, 1172-1181 (2026). DOI： 10.1038/s41377-026-02188-7.

摘要

Abstract

Optical neural networks (ONNs) are emerging as a promising neuromorphic computing paradigm for object recognition

offering unprecedented advantages in light-speed computation

ultra-low power consumption

and inherent parallelism. However

most of ONNs are only capable of performing simple object classification tasks. These tasks are typically constrained to single-object scenarios

which limits their practical applications in multi-object recognition tasks. Here

we propose an anti-interference diffractive deep neural network (AI D

NN) that can accurately and robustly recognize targets in multi-object scenarios

including intra-class

inter-class

and dynamic interference. By employing different deep-learning-based training strategies for targets and interference

two transmissive diffractive layers form a physical network that maps the spatial information of targets all-optically into the power spectrum of the output light

while dispersing all interference as background noise. We demonstrate the effectiveness of this framework in classifying unknown handwritten digits under dynamic scenarios involving 40 categories of interference

achieving a simulated blind testing accuracy of 87.4% using terahertz waves. The presented framework can be physically scaled to operate at any electromagnetic wavelength by simply scaling the diffractive features in proportion to the wavelength range of interest. This work can greatly advance the practical application of ONNs in target recognition and pave the way for the development of real-time

high-throughput

low-power all-optical computing systems

which are expected to be

applied to autonomous driving perception

precision medical diagnosis

and intelligent security monitoring.

关键词

Keywords

references

Kalake, L. et al. Analysis based on recent deep learning approaches applied in real-time multi-object tracking: a review. IEEE Access 9 , 32650–32671 (2021)..

Sun, S. J. et al. Deep affinity network for multiple object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 43 , 104–119 (2021)..

Yan H. et al. MIML-FCN plus: multi-instance multi-label learning via fully convolutional networks with privileged information. in Proc. 30th IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017)..

Yang, X. H. et al. Deep transfer learning-based multi-object detection for plant stomata phenotypic traits intelligent recognition. IEEE/ACM Trans. Audio Speech Lang. Process 20 , 321–329 (2023)..

Chen, Z. D. et al. High-resolution feature pyramid network for small object detection on drone view. IEEE Trans. Circuits Syst. Video Technol. 34 , 475–489 (2024)..

Zheng, H. Y. et al. Multichannel meta-imagers for accelerating machine vision. Nat. Nanotechnol. 19 , 471–478 (2024)..

Zaidi, S. S. A. et al. A survey of modern deep learning based object detection models. Digit. Signal. Process 126 , 103514 (2022)..

Kong, L. Y. et al. LocaLock: enhancing multi-object tracking in satellite videos via local feature matching. Remote Sens 17 , 371 (2025)..

Zhu, T. Y. et al. Looking beyond two frames: end-to-end multi-object tracking using spatial and temporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45 , 12783–12797 (2023)..

Wen, T. et al. Semantically enhanced multi-object detection and tracking for autonomous vehicles. IEEE Trans. Rob. 39 , 4600–4615 (2023)..

Chen, T. I. et al. Dual-awareness attention for few-shot object detection. IEEE Trans. Multimed. 25 , 291–301 (2023)..

Zhu, L. C. et al. Label independent memory for semi-supervised few-shot video classification. IEEE Trans. Pattern Anal. Mach. Intell. 44 , 273–285 (2022)..

Wang, L. M. et al. Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41 , 2740–2755 (2019)..

Li, Z. Y. et al. VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166 , 41–50 (2018)..

Lin, Z. J. et al. 120 GOPS Photonic tensor core in thin-film lithium niobate for inference and in situ training. Nat. Commun. 15 , 1–10 (2024)..

Feldmann, J. et al. Parallel convolutional processing using an integrated photonic tensor core. Nature 589 , 52–58 (2021)..

Miller, D. A. B. Attojoule optoelectronics for low-energy information processing and communications. J. Lightwave Technol. 35 , 346–396 (2017)..

Lee, S. H. et al. Nanoscale resistive switching devices for memory and computing applications. Nano Res. 13 , 1228–1243 (2020)..

Feng, F. et al. Symbiotic evolution of photonics and artificial intelligence: a comprehensive review. Adv. Photonics 7 , 024001 (2025)..

Lin , X. et al. All-optical machine learning using diffractive deep neural networks. Science 361 , 1004–1008 (2018)..

Ashtiani, F. et al. An on-chip photonic deep neural network for image classification. Nature 606 , 501–506 (2022)..

Bai, B. J. et al. All-optical image classification through unknown random diffusers using a single-pixel diffractive network. Light Sci. Appl. 12 , 14 (2023)..

Huang, Z. B. et al. All-optical signal processing of vortex beams with diffractive deep neural networks. Phys. Rev. Appl. 15 , 36936–36952 (2021)..

Chen, Z. J. et al. Deep learning with coherent VCSEL neural networks. Nat. Photonics 17 , 723–730 (2023)..

Hu, J. T. et al. Diffractive optical computing in free space. Nat. Commun. 15 , 1–21 (2024)..

Wetzstein, G. et al. Inference in artificial intelligence with deep optics and photonics. Nature 588 , 39–47 (2020)..

Zou, X. P. F. et al. Target recognition based on pre-processing in computational ghost imaging with deep learning. Opt. Laser Technol. 167 , 1–9 (2023)..

Jiang, Y. et al. Photonic convolution neural network based on interleaved time-wavelength modulation. J. Lightwave Technol. 39 , 4592–4600 (2021)..

Li, J. X. et al. Massively parallel universal linear transformations using a wavelength-multiplexed diffractive optical network. Adv. Photonics 5 , 016003 (2023)..

Chi, H. X. et al. Metasurface enabled multi-target and multi-wavelength diffraction neural networks. Laser Photonics Rev. 19 , 158 (2025)..

Duan, Z. Y. et al. Optical multi-task learning using multi-wavelength diffractive deep neural networks. Nanophotonics 12 , 893–903 (2023)..

Xiang, C. X. et al. Multiplexed metasurfaces for diffractive optics via a phase correlation method. Opt. Lett. 50 , 1989–1992 (2025)..

Luo, Y. et al. Design of task-specific optical systems using broadband diffractive neural networks. Light Sci. Appl. 8 , 112 (2019)..

Li, J. X. et al. Polarization multiplexed diffractive computing: all-optical implementation of a group of linear transformations through a polarization-encoded diffractive network. Light Sci. Appl. 11 , 153 (2022)..

Luo, X. H. et al. Metasurface-enabled on-chip multiplexed diffractive neural networks in the visible. Light Sci. Appl 11 , 158 (2022)..

Wang, Y. Z. et al. Matrix diffractive deep neural networks merging polarization into meta-devices. Laser Photonics Rev. 18 , 2300903 (2024)..

Li, B. L. et al. Orbital angular momentum optical communications enhanced by artificial intelligence. J. Opt. 24 , 094003 (2022)..

Fang, X. Y. et al. Orbital angular momentum-mediated machine learning for high-accuracy mode-feature encoding. Light Sci. Appl. 13 , 49 (2024)..

Cheng, J. W. et al. Multimodal deep learning using on-chip diffractive optics with in situ training capability. Nat. Commun. 15 , 6189 (2024)..

Wei, M. L. et al. Electrically programmable phase-change photonic memory for optical neural networks with nanoseconds in situ training capability. Adv. Photonics 5 , 046004 (2023)..

Xu, S. F. et al. High-order tensor flow processing using integrated photonic circuits. Nat. Commun. 13 , 7970 (2022)..

Tait, A. N. et al. Neuromorphic photonic networks using silicon photonic weight banks. Sci. Rep. 7 , 7430 (2017)..

Wu, C. M. et al. Programmable phase-change metasurfaces on waveguides for multimode photonic convolutional neural network. Nat. Commun. 12 , 96 (2021)..

Guarino, A. et al. Electro-optically tunable microring resonators in lithium niobate. Nat. Photonics 1 , 407–410 (2007)..

Zhu, D. et al. Integrated photonics on thin-film lithium niobate. Adv. Opt. Photonics 13 , 242–352 (2021)..

Chen, Y. T. et al. All-analog photoelectronic chip for high-speed vision tasks. Nature 623 , 48–57 (2023)..

Dong, B. et al. Partial coherence enhances parallelized photonic computing. Nature 632 , 55–62 (2024)..

Qin, J. et al. All-optical Fourier neural network using partially coherent light. Chip 4 , 100140 (2025)..

He, C. et al. Pluggable multitask diffractive neural networks based on cascaded metasurfaces. Opto-Electron. Adv. 7 , 230005 (2024)..

Bai, B. J. et al. Pyramid diffractive optical networks for unidirectional image magnification and demagnification. Light Sci. Appl. 13 , 178 (2024)..

Bai, B. J. et al. To image, or not to image: class-specific diffractive cameras with all-optical erasure of undesired objects. Elight 2 , 14 (2022)..

Ma, G. D. et al. Unidirectional imaging with partially coherent light. Adv. Photonics Nexus 3 , 066008 (2024)..

Xu, Z. H. et al. Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence. Science 384 , 202–209 (2024)..

Zhang, H. et al. An optical neural chip for implementing complex-valued neural network. Nat. Commun. 12 , 457 (2021)..

Xue, Z. W. et al. Fully forward mode training for optical neural networks. Nature 632 , 280–286 (2024)..

Li, J. X. et al. Class-specific differential detection in diffractive optical neural networks improves inference accuracy. Adv. Photonics 1 , 046001 (2019)..

Zhu, H. H. et al. Space-efficientoptical computing with an integrated chip diffractive neural network. Nat. Commun. 13 , 1044 (2022)..

Qian, C. et al. Dynamic recognition and mirage using neuro-metamaterials. Nat. Commun. 13 , 2694 (2022)..

Huang, Z. et al. Pre-sensor computing with compact multilayer optical neural network. Sci. Adv. 10 , eado8516 (2024)..

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰