用于玻璃分割的具有更宽捕捉器的傅里叶边界特征网络
Fourier Boundary Features Network with Wider Catchers for Glass Segmentation
AI总结:
针对玻璃边界模糊及深层特征过度捕捉问题,提出FBWC,通过宽浅层分支、WCC、CTA和可学习FCC增强边界与区域分割,并在三个公开数据集上优于SOTA方法。
摘要:
玻璃在很大程度上模糊了现实世界与反射之间的边界。其特殊的透射和反射特性使与机器视觉相关的语义任务受到干扰。因此,如何厘清玻璃形成的边界,并避免在深层结构中过度捕捉特征而将其作为假阳性信息,对于约束反射表面分割和透视玻璃分割至关重要。我们提出了具有更宽捕捉器的傅里叶边界特征网络(Fourier Boundary Features Network with Wider Catchers,FBWC),这可能是首次尝试利用足够宽的水平浅层分支而不进行纵向加深,以通过初级玻璃语义信息引导细粒度分割边界。具体而言,我们设计了更宽粗略捕捉器(Wider Coarse-Catchers,WCC),用于锚定大面积分割,并从结构角度减少过度提取。我们通过交叉转置注意力(Cross Transpose Attention,CTA)嵌入细粒度特征,引入该机制是为了避免由反射噪声导致的边界内区域不完整。为挖掘玻璃特征并平衡高低层上下文,提出了一种可学习的傅里叶卷积控制器(Fourier Convolution Controller,FCC),以稳健地调节信息整合。所提方法已在三个不同的公开玻璃分割数据集上得到验证。实验结果表明,与玻璃图像分割中的最先进(state-of-the-art,SOTA)方法相比,所提方法取得了更优的分割性能。
英文摘要:
Glass largely blurs the boundary between the real world and the reflection. The special transmittance and reflectance quality have confused the semantic tasks related to machine vision. Therefore, how to clear the boundary built by glass, and avoid over-capturing features as false positive information in deep structure, matters for constraining the segmentation of reflection surface and penetrating glass. We proposed the Fourier Boundary Features Network with Wider Catchers (FBWC), which might be the first attempt to utilize sufficiently wide horizontal shallow branches without vertical deepening for guiding the fine granularity segmentation boundary through primary glass semantic information. Specifically, we designed the Wider Coarse-Catchers (WCC) for anchoring large area segmentation and reducing excessive extraction from a structural perspective. We embed fine-grained features by Cross Transpose Attention (CTA), which is introduced to avoid the incomplete area within the boundary caused by reflection noise. For excavating glass features and balancing high-low layers context, a learnable Fourier Convolution Controller (FCC) is proposed to regulate information integration robustly. The proposed method has been validated on three different public glass segmentation datasets. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art (SOTA) methods in glass image segmentation.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。