Abstract
Objects in an image exhibit diverse scales. Adaptive receptive fields are expected to catch suitable range of context for accurate pixel level semantic prediction for handling objects of diverse sizes. Recently, atrous convolution with different dilation rates has been used to generate features of multi-scales through several branches and these features are fused for prediction. However, there is a lack of explicit interaction among the branches to adaptively make full use of the contexts. In this paper, we propose a Content-Adaptive Scale Interaction Network (CaseNet) to exploit the multi-scale features for scene parsing. We build the CaseNet based on the classic Atrous Spatial Pyramid Pooling (ASPP) module, followed by the proposed contextual scale interaction (CSI) module, and the scale adaptation (SA) module. Specifically, first, for each spatial position, we enable context interaction among different scales through scale-aware non-local operations across the scales, \ie, CSI module, which facilitates the generation of flexible mixed receptive fields, instead of a traditional flat one. Second, the scale adaptation module (SA) explicitly and softly selects the suitable scale for each spatial position and each channel. Ablation studies demonstrate the effectiveness of the proposed modules. We achieve state-of-the-art performance on three scene parsing benchmarks Cityscapes, ADE20K and LIP.
Abstract (translated)
图像中的对象显示出不同的比例。自适应接收字段可以捕获合适的上下文范围,以便准确地预测像素级语义,以处理不同大小的对象。近年来,利用不同扩张率的阿托拉斯卷积,通过多个分支产生多尺度的特征,并将这些特征融合进行预测。然而,分支之间缺乏明确的交互,无法适应地充分利用上下文。本文提出了一种内容自适应尺度交互网络(CASENET),利用多尺度特征进行场景分析。基于经典的阿托罗斯空间金字塔池(ASPP)模型,建立了案例网,接着提出了上下文尺度交互(CSI)模型和尺度适应(SA)模型。具体来说,首先,对于每个空间位置,我们通过跨尺度的感知尺度的非本地操作(即CSI模块)实现不同尺度之间的上下文交互,这有助于生成灵活的混合接收字段,而不是传统的平坦接收字段。其次,尺度适应模块(SA)明确而柔和地为每个空间位置和每个通道选择合适的尺度。烧蚀研究证明了所提出模块的有效性。我们在三个场景分析基准城市景观、ADE20K和LIP上实现了最先进的性能。
URL
https://arxiv.org/abs/1904.08170