Recently, advancements in deep learning-based superpixel segmentation methods
have brought about improvements in both the efficiency and the performance of
segmentation. However, a significant challenge remains in generating
superpixels that strictly adhere to object boundaries while conveying rich
visual significance, especially when cross-surface color correlations may
interfere with objects. Drawing inspiration from neural structure and visual
mechanisms, we propose a biological network architecture comprising an Enhanced
Screening Module (ESM) and a novel Boundary-Aware Label (BAL) for superpixel
segmentation. The ESM enhances semantic information by simulating the
interactive projection mechanisms of the visual cortex. Additionally, the BAL
emulates the spatial frequency characteristics of visual cortical cells to
facilitate the generation of superpixels with strong boundary adherence. We
demonstrate the effectiveness of our approach through evaluations on both the
BSDS500 dataset and the NYUv2 dataset.

通过采用基于深度学习的超像素分割方法，在生成严格遵循物体边界的超像素，并传达丰富的视觉意义的过程中存在许多挑战，尤其当面色交叉相关性可能干扰物体时。为了解决这些问题，从神经结构和视觉机制中获得灵感，提出了一种生物网络架构，包括增强筛选模块和新颖的边界感知标签，用于超像素分割。增强筛选模块通过模拟视觉皮层的交互投影机制来增强语义信息。此外，边界感知标签模拟视觉皮层细胞的空间频率特性，以促进生成具有较强边界贴合性的超像素。通过对 BSDS500 数据集和 NYUv2 数据集的评估，证明了该方法的有效性。