# Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks

arXiv: https://arxiv.org/abs/1902.07474 · HTML: https://mlsanity.com/paper/1902.07474/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes](https://mlsanity.com/paper/2110.08059/) (2021)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [Decoupled Dynamic Filter Networks](https://mlsanity.com/paper/2104.14107/) (2021)
- [PointConvFormer: Revenge of the Point-based Convolution](https://mlsanity.com/paper/2208.02879/) (2022)
- [Dynamic Sparse Network for Time Series Classification: Learning What to "see''](https://mlsanity.com/paper/2212.09840/) (2022)
- [Fast Object Placement Assessment](https://mlsanity.com/paper/2205.14280/) (2022)
- [Investigating Neural Architectures by Synthetic Dataset Design](https://mlsanity.com/paper/2204.11045/) (2022)

## Abstract (arXiv)

Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions involve large kernels, down/up-sampling and dilated convolutions. These require testing a variety of dilation and down/up-sampling factors and result in non-compact representations and excessive number of parameters. We address this issue by proposing a new convolution filter composed of displaced aggregation units (DAU). DAUs learn spatial displacements and adapt the receptive field sizes of individual convolution filters to a given problem, thus eliminating the need for hand-crafted modifications. DAUs provide a seamless substitution of convolutional filters in existing state-of-the-art architectures, which we demonstrate on AlexNet, ResNet50, ResNet101, DeepLab and SRN-DeblurNet. The benefits of this design are demonstrated on a variety of computer vision tasks and datasets, such as image classification (ILSVRC 2012), semantic segmentation (PASCAL VOC 2011, Cityscape) and blind image de-blurring (GOPRO). Results show that DAUs efficiently allocate parameters resulting in up to four times more compact networks at similar or better performance.