Foreground segmentation models are designed to extract moving objects of varying sizes from the background, which can benefit from representations of various scales. As an effective module for capturing multi-scale contexts, Atrous Spatial Pyramid Pooling (ASPP) convolves a final feature representation via multiple parallel atrous convolutions with different dilation rates. However, as the dilation rate increases, ASPP gradually loses its large-scale modeling ability because the sampling of atrous kernel becomes progressively sparse within the receptive field. To solve this problem, we design a CompactASPP module to convolve feature maps compactly. Without significantly increasing the module size, the CompactASPP can encode multi-scale features from all neurons within the receptive field rather than from neurons in several sparsely distributed positions. Furthermore, we leverage CompactASPP modules to enhance our previous X-Net. The proposed Fast X-Net substantially improves the segmentation speed by over 63.6% and attains new state-of-the-art performances on CDnet2014, SBI2015 and UCSD benchmarks.

前景分割模型旨在从背景中提取大小不同的运动对象，这可以从各种比例的表示中受益。作为捕获多尺度上下文的有效模块，Atrous空间金字塔池（ASPP）通过具有不同膨胀率的多个并行Atrous卷积对最终特征表示进行卷积。但是，随着膨胀率的增加，ASPP逐渐失去了其大规模建模能力，因为对无仁内核的采样在接受域内逐渐稀疏。为了解决这个问题，我们设计了一个CompactASPP模块来紧凑地卷积特征图。。在不显着增加模块大小的情况下，CompactASPP可以对来自接收域内所有神经元而不是来自几个稀疏分布位置的神经元的多尺度特征进行编码。此外，我们利用CompactASPP模块来增强我们以前的X-Net。拟议的Fast X-Net大大提高了63.6％的分割速度，并在CDnet2014，SBI2015和UCSD基准上获得了最新的最新性能。