A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
Motion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining hig...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/5/286 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327631793651712 |
|---|---|
| author | Tianqi Chen Yuki Todo Zhiyu Qiu Yuxiao Hua Hiroki Sugiura Zheng Tang |
| author_facet | Tianqi Chen Yuki Todo Zhiyu Qiu Yuxiao Hua Hiroki Sugiura Zheng Tang |
| author_sort | Tianqi Chen |
| collection | DOAJ |
| description | Motion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining highly robust. Unlike present deep learning models, which rely on extension of computation and extraction of global features, the HCdM mimics the localized processing of dendritic neurons, enabling efficient motion feature integration. Through synaptic learning that prunes unnecessary parts, our model maintains high accuracy in noised images, particularly against salt-and-pepper noise. Experimental results show that the HCdM reached over 99.5% test accuracy, maintained robust performance under 10% salt-and-pepper noise, and achieved cross-dataset generalization exceeding 80% in certain conditions. Comparisons with state-of-the-art (SOTA) models like vision transformers (ViTs) and convolutional neural networks (CNNs) demonstrate the HCdM’s robustness and efficiency. Additionally, in contrast to previous artificial visual systems (AVSs), our findings suggest that lateral geniculate nucleus (LGN) structures, though present in biological vision, may not be essential for motion direction detection. This insight provides a new direction for bio-inspired computational models. Future research will focus on hybridizing the HCdM with SOTA models that perform well on complex visual scenes to enhance its adaptability. |
| format | Article |
| id | doaj-art-37958391b14f40fda4eeb226c387a20c |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-37958391b14f40fda4eeb226c387a20c2025-08-20T03:47:49ZengMDPI AGBiomimetics2313-76732025-05-0110528610.3390/biomimetics10050286A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal CellsTianqi Chen0Yuki Todo1Zhiyu Qiu2Yuxiao Hua3Hiroki Sugiura4Zheng Tang5Division of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanFaculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa 920-1192, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanInstitute of AI for Industries, Chinese Academy of Sciences Nanjing, Nanjing 210008, ChinaMotion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining highly robust. Unlike present deep learning models, which rely on extension of computation and extraction of global features, the HCdM mimics the localized processing of dendritic neurons, enabling efficient motion feature integration. Through synaptic learning that prunes unnecessary parts, our model maintains high accuracy in noised images, particularly against salt-and-pepper noise. Experimental results show that the HCdM reached over 99.5% test accuracy, maintained robust performance under 10% salt-and-pepper noise, and achieved cross-dataset generalization exceeding 80% in certain conditions. Comparisons with state-of-the-art (SOTA) models like vision transformers (ViTs) and convolutional neural networks (CNNs) demonstrate the HCdM’s robustness and efficiency. Additionally, in contrast to previous artificial visual systems (AVSs), our findings suggest that lateral geniculate nucleus (LGN) structures, though present in biological vision, may not be essential for motion direction detection. This insight provides a new direction for bio-inspired computational models. Future research will focus on hybridizing the HCdM with SOTA models that perform well on complex visual scenes to enhance its adaptability.https://www.mdpi.com/2313-7673/10/5/286motion direction detectionartificial visual systemdendritic neuron modelsynaptic learningmachine learningbio-inspired model |
| spellingShingle | Tianqi Chen Yuki Todo Zhiyu Qiu Yuxiao Hua Hiroki Sugiura Zheng Tang A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells Biomimetics motion direction detection artificial visual system dendritic neuron model synaptic learning machine learning bio-inspired model |
| title | A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells |
| title_full | A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells |
| title_fullStr | A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells |
| title_full_unstemmed | A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells |
| title_short | A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells |
| title_sort | bio inspired learning dendritic motion detection framework with direction selective horizontal cells |
| topic | motion direction detection artificial visual system dendritic neuron model synaptic learning machine learning bio-inspired model |
| url | https://www.mdpi.com/2313-7673/10/5/286 |
| work_keys_str_mv | AT tianqichen abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT yukitodo abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT zhiyuqiu abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT yuxiaohua abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT hirokisugiura abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT zhengtang abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT tianqichen bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT yukitodo bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT zhiyuqiu bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT yuxiaohua bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT hirokisugiura bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells AT zhengtang bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells |