Rethinking Polyp Segmentation from An Out-of distribution Perspective

doi:10.1007/s11633-023-1472-2

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Rethinking Polyp Segmentation from An Out-ofdistribution Perspective
	Ge-Peng Ji 1; Jing Zhang 1; Dylan Campbell 1; Huan Xiong 2; Nick Barnes 1
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:4 页码:631-639
摘要	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 (i.e., 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.
关键词	Polyp segmentation anomaly segmentation out-of-distribution segmentation masked autoencoder abdomen
DOI	10.1007/s11633-023-1472-2
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58563
专题	学术期刊_Machine Intelligence Research
作者单位	1.Australian National University, Canberra 8105, Australia 2.Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi 999041, UAE
推荐引用方式 GB/T 7714	Ge-Peng Ji,Jing Zhang,Dylan Campbell,et al. Rethinking Polyp Segmentation from An Out-ofdistribution Perspective[J]. Machine Intelligence Research,2024,21(4):631-639.
APA	Ge-Peng Ji,Jing Zhang,Dylan Campbell,Huan Xiong,&Nick Barnes.(2024).Rethinking Polyp Segmentation from An Out-ofdistribution Perspective.Machine Intelligence Research,21(4),631-639.
MLA	Ge-Peng Ji,et al."Rethinking Polyp Segmentation from An Out-ofdistribution Perspective".Machine Intelligence Research 21.4(2024):631-639.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2023-06-092.pdf（2420KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载