一个复合眼灵感的多尺度神经架构,集成注意力机制
Ferrante Neri1,2, Mengchen Yang1, Yu Xue1
1Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, P. R. China.
International journal of neural systems
|September 22, 2025
概括
一个新的混合神经网络CompEyeNet通过整合变压器和卷积结构来增强视觉任务. 这种生物启发型模型改善了多尺度特征表示,并且与现有模型相比,在更少的参数下实现了更高的准确性.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 生物启发的计算技术
背景情况:
- 多尺度特征和上下文信息的有效整合对于神经系统结构建模和复杂的视觉任务至关重要.
- 现有的模型经常在平衡全球和本地特征表示效率方面扎.
研究的目的:
- 提出CompEyeNet,一个生物启发的混合神经网络架构.
- 增强复杂视觉任务的多尺度信息表示和重建能力.
主要方法:
- 开发了一个混合架构,结合了变压器 (MATBN) 和轻质卷积结构 (CENN).
- 对于局部和远程依赖,MATBN利用了多个注意力机制.
- CENN 增强了高分辨率的特征层和注意力融合,以实现多尺度表示.
主要成果:
- 在医学图像细分数据集 (MICCAI-CVC-ClinicDB,ISIC2018,MICCAI-牙细分) 上,CompEyeNet表现出卓越的性能.
- 与Deeplab,Unet和YOLO系列相比,使用更少的参数实现了更好的性能.
- 与YOLOv11相比,参数减少了38.31%,改善了子,雅卡德,精度和回忆.
结论:
- 在神经系统建模和图像分析的参数效率和准确性方面,CompEyeNet提供了显著的优势.
- 生物启发的注意力融合混合神经网络显示了广泛的应用潜力.
相关概念视频
Visual System
1.7K
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
1.7K
Vision
59.4K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
59.4K
Parallel Processing
638
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
638


