A differentiable Gaussian Prototype Layer for explainable Segmentation
원문 초록
We introduce a Gaussian Prototype Layer for gradient-based prototype learning and demonstrate two novel network architectures for explainable segmentation one of which relies on region proposals. Both models are evaluated on agricultural datasets. While Gaussian Mixture Models (GMMs) have been used to model latent distributions of neural networks before, they are typically fitted using the EM algorithm. Instead, the proposed prototype layer relies on gradient-based optimization and hence allows for end-to-end training. This facilitates development and allows to use the full potential of a trainable deep feature extractor. We show that it can be used as a novel building block for explainable neural networks. We employ our Gaussian Prototype Layer in (1) a model where prototypes are detected in the latent grid and (2) a model inspired by Fast-RCNN with SLIC superpixels as region proposals. The earlier achieves a similar performance as compared to the state-of-the art while the latter has the benefit of a more precise prototype localization that comes at the cost of slightly lower accuracies. By introducing a gradient-based GMM layer we combine the benefits of end-to-end training with the simplicity and theoretical foundation of GMMs which will allow to adapt existing semi-supervised learning strategies for prototypical part models in future.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering
Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens
STA-Unet: Rethink the semantic redundant for Medical Imaging Segmentation
A comprehensive review and new taxonomy on superpixel segmentation
ESA: Annotation-Efficient Active Learning for Semantic Segmentation
Persistence Image from 3D Medical Image: Superpixel and Optimized Gaussian Coefficient
토론
이 논문과 연결된 포럼 글이 아직 없습니다.