# Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling

arXiv: https://arxiv.org/abs/2404.03991 · HTML: https://mlsanity.com/paper/2404.03991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 5 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation](https://mlsanity.com/paper/1803.06815/) (2018)
- [Auxiliary Tasks in Multi-task Learning](https://mlsanity.com/paper/1805.06334/) (2018)
- [SoftSeg: Advantages of soft versus binary training for image segmentation](https://mlsanity.com/paper/2011.09041/) (2020)
- [Using Soft Labels to Model Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/2109.12622/) (2021)
- [MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2103.13044/) (2021)
- [Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN](https://mlsanity.com/paper/2302.10484/) (2023)
- [Superpixel-Guided Label Softening for Medical Image Segmentation](https://mlsanity.com/paper/2007.08897/) (2020)
- [Soft labelling for semantic segmentation: Bringing coherence to label down-sampling](https://mlsanity.com/paper/2302.13961/) (2023)
- [Lightweight Encoder-Decoder Architecture for Foot Ulcer Segmentation](https://mlsanity.com/paper/2207.02515/) (2022)

## Abstract (arXiv)

Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images accurately and predict detailed labels, resulting in diminished performance compared to processing at original resolutions. This situation exemplifies the trade-off between efficiency and accuracy, with higher downsampling factors further impairing segmentation outcomes. Preserving information during downsampling is especially critical for medical image segmentation tasks. To tackle this challenge, we introduce a novel method named Edge-preserving Probabilistic Downsampling (EPD). It utilizes class uncertainty within a local window to produce soft labels, with the window size dictating the downsampling factor. This enables a network to produce quality predictions at low resolutions. Beyond preserving edge details more effectively than conventional nearest-neighbor downsampling, employing a similar algorithm for images, it surpasses bilinear interpolation in image downsampling, enhancing overall performance. Our method significantly improved Intersection over Union (IoU) to 2.85%, 8.65%, and 11.89% when downsampling data to 1/2, 1/4, and 1/8, respectively, compared to conventional interpolation methods.