# How Can CNNs Use Image Position for Segmentation?

arXiv: https://arxiv.org/abs/2005.03463 · HTML: https://mlsanity.com/paper/2005.03463/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 8 of 8)

- [Medical Image Segmentation Using Squeeze-and-Expansion Transformers](https://mlsanity.com/paper/2105.09511/) (2021)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation](https://mlsanity.com/paper/2112.01036/) (2021)
- [Leveraging Global Binary Masks for Structure Segmentation in Medical Images](https://mlsanity.com/paper/2205.09107/) (2022)
- [CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning](https://mlsanity.com/paper/2302.02330/) (2023)
- [Residual Moment Loss for Medical Image Segmentation](https://mlsanity.com/paper/2106.14178/) (2021)
- [Lane detection with Position Embedding](https://mlsanity.com/paper/2203.12301/) (2022)
- [Hybrid Attention Network for Accurate Breast Tumor Segmentation in Ultrasound Images](https://mlsanity.com/paper/2506.16592/) (2025)

## Abstract (arXiv)

Convolution is an equivariant operation, and image position does not affect its result. A recent study shows that the zero-padding employed in convolutional layers of CNNs provides position information to the CNNs. The study further claims that the position information enables accurate inference for several tasks, such as object recognition, segmentation, etc. However, there is a technical issue with the design of the experiments of the study, and thus the correctness of the claim is yet to be verified. Moreover, the absolute image position may not be essential for the segmentation of natural images, in which target objects will appear at any image position. In this study, we investigate how positional information is and can be utilized for segmentation tasks. Toward this end, we consider em positional encoding (PE) that adds channels embedding image position to the input images and compare PE with several padding methods. Considering the above nature of natural images, we choose medical image segmentation tasks, in which the absolute position appears to be relatively important, as the same organs (of different patients) are captured in similar sizes and positions. We draw a mixed conclusion from the experimental results; the positional encoding certainly works in some cases, but the absolute image position may not be so important for segmentation tasks as we think.