论文标题
定位用于加速图像分类的语义补丁
Localizing Semantic Patches for Accelerating Image Classification
论文作者
论文摘要
现有作品通常集中于减少架构冗余以加速图像分类，但忽略输入图像的空间冗余。本文提出了有效的图像分类管道来解决此问题。我们首先通过称为Anchornet的轻量级补丁提案网络在输入图像上查明任务感知区域。然后，我们将这些局部语义斑块的空间冗余较小得多地馈送到一个通用分类网络中。与Deep CNN的流行设计不同，我们旨在仔细设计无中间卷积衬托的锚固板的接收场。这样可以确保从高级空间位置到特定输入图像补丁的确切映射。每个补丁的贡献是可以解释的。此外，AnchOrnet与任何下游架构兼容。 Imagenet上的实验结果表明，我们的方法优于SOTA动态推理方法，其推理成本较少。我们的代码可在https://github.com/winycg/anchornet上找到。
Existing works often focus on reducing the architecture redundancy for accelerating image classification but ignore the spatial redundancy of the input image. This paper proposes an efficient image classification pipeline to solve this problem. We first pinpoint task-aware regions over the input image by a lightweight patch proposal network called AnchorNet. We then feed these localized semantic patches with much smaller spatial redundancy into a general classification network. Unlike the popular design of deep CNN, we aim to carefully design the Receptive Field of AnchorNet without intermediate convolutional paddings. This ensures the exact mapping from a high-level spatial location to the specific input image patch. The contribution of each patch is interpretable. Moreover, AnchorNet is compatible with any downstream architecture. Experimental results on ImageNet show that our method outperforms SOTA dynamic inference methods with fewer inference costs. Our code is available at https://github.com/winycg/AnchorNet.
