Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913047098949632 |
|---|---|
| author | Shao, Feixue Shi, Guangze Liu, Xueyu Wu, Yongfei Wei, Mingqiang Zhang, Jianan Lu, Jianbo Yan, Guiying Yang, Weihua |
| author_facet | Shao, Feixue Shi, Guangze Liu, Xueyu Wu, Yongfei Wei, Mingqiang Zhang, Jianan Lu, Jianbo Yan, Guiying Yang, Weihua |
| contents | Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, current approaches are often constrained by the systematic and stochastic gaps between neural and visual modalities, largely neglecting the intrinsic computational mechanisms of the Human Visual System (HVS). To address this, we propose Brain-Inspired Capture (BI-Cap), a neuromimetic perceptual simulation paradigm that aligns these modalities by emulating HVS processing. Specifically, we construct a neuromimetic pipeline comprising four biologically plausible dynamic and static transformations, coupled with Mutual Information (MI)-guided dynamic blur regulation to simulate adaptive visual processing. Furthermore, to mitigate the inherent non-stationarity of neural activity, we introduce an evidence-driven latent space representation. This formulation explicitly models uncertainty, thereby ensuring robust neural embeddings. Extensive evaluations on zero-shot brain-to-image retrieval across two public benchmarks demonstrate that BI-Cap substantially outperforms state-of-the-art methods, achieving relative gains of 9.2\% and 8.0\%, respectively. We have released the source code on GitHub through the link https://github.com/flysnow1024/BI-Cap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17927 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding Shao, Feixue Shi, Guangze Liu, Xueyu Wu, Yongfei Wei, Mingqiang Zhang, Jianan Lu, Jianbo Yan, Guiying Yang, Weihua Computer Vision and Pattern Recognition Artificial Intelligence Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, current approaches are often constrained by the systematic and stochastic gaps between neural and visual modalities, largely neglecting the intrinsic computational mechanisms of the Human Visual System (HVS). To address this, we propose Brain-Inspired Capture (BI-Cap), a neuromimetic perceptual simulation paradigm that aligns these modalities by emulating HVS processing. Specifically, we construct a neuromimetic pipeline comprising four biologically plausible dynamic and static transformations, coupled with Mutual Information (MI)-guided dynamic blur regulation to simulate adaptive visual processing. Furthermore, to mitigate the inherent non-stationarity of neural activity, we introduce an evidence-driven latent space representation. This formulation explicitly models uncertainty, thereby ensuring robust neural embeddings. Extensive evaluations on zero-shot brain-to-image retrieval across two public benchmarks demonstrate that BI-Cap substantially outperforms state-of-the-art methods, achieving relative gains of 9.2\% and 8.0\%, respectively. We have released the source code on GitHub through the link https://github.com/flysnow1024/BI-Cap. |
| title | Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17927 |