# Towards a New Interpretation of Separable Convolutions

arXiv: https://arxiv.org/abs/1701.04489 · HTML: https://mlsanity.com/paper/1701.04489/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2017.

## Built on by (most cited first, 1 of 1)

- [Faster Convolution Inference Through Using Pre-Calculated Lookup Tables](https://mlsanity.com/paper/2104.01681/) (2021)

## Abstract (arXiv)

In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored. Several researchers, most notably (Chollet, 2016) and (Ghosh, 2017) have used separable convolutions in their deep architectures and have demonstrated state of the art or close to state of the art performance. However, the underlying mechanism of action of separable convolutions are still not fully understood. Although their mathematical definition is well understood as a depthwise convolution followed by a pointwise convolution, deeper interpretations such as the extreme Inception hypothesis (Chollet, 2016) have failed to provide a thorough explanation of their efficacy. In this paper, we propose a hybrid interpretation that we believe is a better model for explaining the efficacy of separable convolutions.