ComputingBiomedical EngineeringComputer ScienceBiomedical ImagingComputer VisionMachine LearningDeep LearningImage SegmentationMedical Image AnalysisMedical ImagingRepresentation LearningAdaptive QuantizationFew-shot LearningFew-shot SegmentationQuantizationSelf-organized StructuresVector Quantization
The existing few-shot medical segmentation networks share the same practice that the more prototypes, the better performance. This phenomenon can be theoretically interpreted in Vector Quantization (VQ) view: the more prototypes, the more clusters are separated from pixel-wise feature points distributed over the full space. However, as we further think about few-shot segmentation with this perspective, it is found that the clusterization of feature points and the adaptation to unseen tasks have not received enough attention. Motivated by the observation, we propose a learning VQ mechanism consisting of grid-format VQ (GFVQ), self-organized VQ (SOVQ) and residual oriented VQ (ROVQ). To be specific, GFVQ generates the prototype matrix by averaging square grids over the spatial extent, which uniformly quantizes the local details; SOVQ adaptively assigns the feature points to different local classes and creates a new representation space where the learnable local prototypes are updated with a global view; ROVQ introduces residual information to fine-tune the aforementioned learned local prototypes without retraining, which benefits the generalization performance for the irrelevance to the training task. We empirically show that our VQ framework yields the state-of-the-art performance over abdomen, cardiac and prostate MRI datasets and expect this work will provoke a rethink of the current few-shot medical segmentation model design. Our code will soon be publicly available.
30
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Teuvo Kohonen · Proceedings of the IEEE · 1990 · 8.2K citations
Hoo-Chang Shin, Holger R. Roth, Mingchen Gao et al. · IEEE Transactions on Medical Imaging · 2016 · 5.8K citations · Full text
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard S. Zemel · arXiv (Cornell University) · 2017 · 5.2K citations · Full text
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment
Kaixin Wang, Jun Hao Liew, Yingtian Zou et al. · 2019 · 1.4K citations