论文标题
稳定分割的矢量量化
Vector Quantisation for Robust Segmentation
论文作者
论文摘要
分割模型在医疗域中的可靠性取决于模型对输入空间中扰动的鲁棒性。鲁棒性是医学成像中的一个特别挑战，展示了各种图像噪声，腐败和领域变化的来源。通常通过模拟异质环境来尝试获得鲁棒性，要么以数据增强的形式启发，要么通过学习以对抗性方式产生特定的扰动。我们提出并证明在低维嵌入空间中学习离散表示可以改善分割模型的鲁棒性。这是通过称为矢量定量的字典学习方法来实现的。我们使用一组设计的实验来分析域移位和输入空间中的噪声扰动下的潜在和输出空间的鲁棒性。我们适应流行的UNET架构，在瓶颈中插入一个定量块。我们证明了在三个分割任务上的分割精度和更好的鲁棒性。代码可在\ url {https://github.com/ainkaransanthi/vector-quantisation-for-robust-mentegation}中获得。
The reliability of segmentation models in the medical domain depends on the model's robustness to perturbations in the input space. Robustness is a particular challenge in medical imaging exhibiting various sources of image noise, corruptions, and domain shifts. Obtaining robustness is often attempted via simulating heterogeneous environments, either heuristically in the form of data augmentation or by learning to generate specific perturbations in an adversarial manner. We propose and justify that learning a discrete representation in a low dimensional embedding space improves robustness of a segmentation model. This is achieved with a dictionary learning method called vector quantisation. We use a set of experiments designed to analyse robustness in both the latent and output space under domain shift and noise perturbations in the input space. We adapt the popular UNet architecture, inserting a quantisation block in the bottleneck. We demonstrate improved segmentation accuracy and better robustness on three segmentation tasks. Code is available at \url{https://github.com/AinkaranSanthi/Vector-Quantisation-for-Robust-Segmentation}
