pith. sign in

arxiv: 2306.07792 · v1 · pith:YEJAJGJEnew · submitted 2023-06-13 · 📡 eess.IV · cs.CV

Rethinking Polyp Segmentation from an Out-of-Distribution Perspective

classification 📡 eess.IV cs.CV
keywords out-of-distributionsegmentationpolypdistributionhealthyimagesperspectivereconstruction
0
0 comments X
read the original abstract

Unlike existing fully-supervised approaches, we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning approach. We leverage the ability of masked autoencoders -- self-supervised vision transformers trained on a reconstruction task -- to learn in-distribution representations; here, the distribution of healthy colon images. We then perform out-of-distribution reconstruction and inference, with feature space standardisation to align the latent distribution of the diverse abnormal samples with the statistics of the healthy samples. We generate per-pixel anomaly scores for each image by calculating the difference between the input and reconstructed images and use this signal for out-of-distribution (ie, polyp) segmentation. Experimental results on six benchmarks show that our model has excellent segmentation performance and generalises across datasets. Our code is publicly available at https://github.com/GewelsJI/Polyp-OOD.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.