Skip to main content

Research Repository

Advanced Search

Clinical Scene Segmentation with Tiny Datasets

Smith, Thomas J.; Sharkey, Don; Crowe, John; Valstar, Michel


Thomas J. Smith

Profile Image

Clinical Associate Professor

John Crowe


Many clinical procedures could benefit from automatic scene segmentation and subsequent action recognition. Using Convolutional Neural Networks to semantically segment meaningful parts of an image or video is still an unsolved problem. This becomes even more apparent when only a small dataset is available. Whilst using RGB as the input is sufficient for a large labelled dataset, achieving high accuracy on a small dataset directly from RGB is difficult. This is because the ratio of free image dimensions to the number of training images is very high, resulting in unavoidable underfitting. We show that the addition of su-perpixels to represent an image in our network improves the semantic segmentation, and that superpixels can be learned to be detected by Convolutional Neural Networks if those superpixels are appropriately represented. Here we present a novel representation for superpixels, multi-channel connected graphs (MCGs). We show how using pre-trained deep learned superpixels used in an end-to-end manner achieve good semantic segmentation results without the need for large quantities of labelled data, by training with only 20 instances for 23 classes.


Smith, T. J., Sharkey, D., Crowe, J., & Valstar, M. (2020). Clinical Scene Segmentation with Tiny Datasets. In 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Conference Name IEEE 17th International Conference on Computer Vision (ICCVW 2019)
Start Date Oct 27, 2019
End Date Nov 2, 2019
Acceptance Date Aug 20, 2019
Online Publication Date Nov 2, 2019
Publication Date Mar 5, 2020
Deposit Date Nov 1, 2019
Publicly Available Date Mar 12, 2020
Book Title 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
Public URL
Publisher URL
Related Public URLs


Smith Clinical Scene Segmentation With Tiny Datasets ICCVW 2019 Paper (1.1 Mb)

You might also like

Downloadable Citations