# Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Padding

arXiv: https://arxiv.org/abs/2307.07725 · HTML: https://mlsanity.com/paper/2307.07725/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Builds on (most cited first, 16 of 16)

- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [How Much Position Information Do Convolutional Neural Networks Encode?](https://mlsanity.com/paper/2001.08248/) (2020)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [On the Turing Completeness of Modern Neural Network Architectures](https://mlsanity.com/paper/1901.03429/) (2019)
- [Positional Encoding as Spatial Inductive Bias in GANs](https://mlsanity.com/paper/2012.05217/) (2020)
- [Mind the Pad -- CNNs can Develop Blind Spots](https://mlsanity.com/paper/2010.02178/) (2020)
- [Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study](https://mlsanity.com/paper/2004.11803/) (2020)
- [Partial Convolution based Padding](https://mlsanity.com/paper/1811.11718/) (2018)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [Toward Spatially Unbiased Generative Models](https://mlsanity.com/paper/2108.01285/) (2021)
- [Convolution with even-sized kernels and symmetric padding](https://mlsanity.com/paper/1903.08385/) (2019)
- [Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics](https://mlsanity.com/paper/2106.11160/) (2021)
- [Learning on the Edge: Explicit Boundary Handling in CNNs](https://mlsanity.com/paper/1805.03106/) (2018)
- [Context-aware Padding for Semantic Segmentation](https://mlsanity.com/paper/2109.07854/) (2021)
- [Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features](https://mlsanity.com/paper/2206.01202/) (2022)

## Abstract (arXiv)

Zero padding is often used in convolutional neural networks to prevent the feature map size from decreasing with each layer. However, recent studies have shown that zero padding promotes encoding of absolute positional information, which may adversely affect the performance of some tasks. In this work, a novel padding method called Peripheral Prediction Padding (PP-Pad) method is proposed, which enables end-to-end training of padding values suitable for each task instead of zero padding. Moreover, novel metrics to quantitatively evaluate the translation invariance of the model are presented. By evaluating with these metrics, it was confirmed that the proposed method achieved higher accuracy and translation invariance than the previous methods in a semantic segmentation task.