论文标题
SSBNET：通过自适应采样提高视觉识别效率
SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling
论文作者
论文摘要
降采样被广泛采用，以实现视觉识别的准确性和延迟之间的良好权衡。不幸的是，没有学习常用的合并层，因此无法保留重要信息。作为另一个降低方法，自适应采样权重和与任务相关的过程区域，因此能够更好地保留有用的信息。但是，自适应抽样的使用仅限于某些层。在本文中，我们表明，在深神经网络的构件中使用自适应采样可以提高其效率。特别是，我们提出了SSBNET，该SSBNET是通过将采样层反复插入Resnet等现有网络构建的。实验结果表明，所提出的SSBNET可以在ImageNet和可可数据集上实现竞争性图像分类和对象检测性能。例如，SSB-Resnet-RS-200在Imagenet数据集上的精度为82.6％，比基线RESNET-RS-152高0.6％，具有相似的复杂性。可视化显示了SSBNET在允许不同层专注于不同位置的优势，而消融研究进一步验证了自适应采样比均匀方法的优势。
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another dimension reduction method, adaptive sampling weights and processes regions that are relevant to the task, and is thus able to better preserve useful information. However, the use of adaptive sampling has been limited to certain layers. In this paper, we show that using adaptive sampling in the building blocks of a deep neural network can improve its efficiency. In particular, we propose SSBNet which is built by inserting sampling layers repeatedly into existing networks like ResNet. Experiment results show that the proposed SSBNet can achieve competitive image classification and object detection performance on ImageNet and COCO datasets. For example, the SSB-ResNet-RS-200 achieved 82.6% accuracy on ImageNet dataset, which is 0.6% higher than the baseline ResNet-RS-152 with a similar complexity. Visualization shows the advantage of SSBNet in allowing different layers to focus on different positions, and ablation studies further validate the advantage of adaptive sampling over uniform methods.
