This paper presents an efficient module named spatial bottleneck for accelerating the convolutional layers in deep neural networks. The core idea is to decompose convolution into two stages, which first reduce the spatial resolution of the feature map, and then restore it to the desired size. This operation decreases the sampling density in the spatial domain, which is independent yet complementary to network acceleration approaches in the channel domain. Using different sampling rates, we can tradeoff between recognition accuracy and model complexity.
As a basic building block, spatial bottleneck can be used to replace any single convolutional layer, or the combination of two convolutional layers. We empirically verify the effectiveness of spatial bottleneck by applying it to the deep residual networks. Spatial bottleneck achieves 2x and 1.4x speedup on the regular and channel-bottlenecked residual blocks, respectively, with the accuracies retained in recognizing low-resolution images, and even improved in recognizing high-resolution images.
AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；Australian Catholic University（澳大利亚天主教大学）；Flinders University（弗林德斯大学）
Accelerating Local AI on Consumer GPUs: A Hardware-Aware Dynamic Strategy for YOLOv10s
School of Computing（计算学院）；Information Sciences Florida International University（信息科学佛罗里达国际大学）；Department of Computer（计算机系）；Information Systems Saint Leo University（信息系统圣路易大学）
