Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a sliding window scheme to extract features. However, not all the windows contribute equally to the prediction results of CNNs. In practice, the convolutional operation on some of the windows (e.g., smooth windows that contain very similar pixels) can be very redundant and may introduce noises into the computation. Such redundancy may not only deteriorate the performance but also incur the unnecessary computational cost. Thus, it is important to reduce the computational redundancy of convolution to improve the performance. To this end, we propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1 ×1 convolutional kernel to replace the original large kernel. In this sense, we are able to effectively avoid the redundant computation on similar pixels. By replacing the standard convolution in CNNs with our CAC, the resultant models yield significantly better performance and lower computational cost than the baseline models with the standard convolution. More critically, we are able to dynamically allocate suitable computation resources according to the data smoothness of different images, making it possible for content-aware computation. Extensive experiments on various computer vision tasks demonstrate the superiority of our method over existing methods.

由于卷积层强大的特征学习能力，卷积神经网络（CNN）取得了巨大的成功。具体来说，标准卷积使用滑动窗口方案遍历输入图像/特征来提取特征。然而，并不是所有的窗口对 CNN 的预测结果都有同样的贡献。在实践中，一些窗口上的卷积操作（例如，包含非常相似像素的平滑窗口）可能非常冗余，并且可能会在计算中引入噪声。这种冗余不仅会降低性能，还会导致不必要的计算成本。因此，重要的是减少卷积的计算冗余以提高性能。为此，我们提出了一种内容感知卷积（CAC），它可以自动检测平滑窗口并应用 1×1 卷积核来替换原始的大核。从这个意义上说，我们能够有效地避免对相似像素的冗余计算。通过用我们的 CAC 替换 CNN 中的标准卷积，与使用标准卷积的基线模型相比，所得模型产生了显着更好的性能和更低的计算成本。更关键的是，我们能够根据不同图像的数据平滑度动态分配合适的计算资源，使内容感知计算成为可能。对各种计算机视觉任务的大量实验证明了我们的方法优于现有方法。