Amortized Learning of Dynamic Feature Scaling for Image Segmentation

Convolutional neural networks (CNN) have become the predominant model for image segmentation tasks. Most CNN segmentation architectures resize spatial dimensions by a fixed factor of two to aggregate spatial context. Recent work has explored using other resizing factors to improve model accuracy for specific applications. However, finding the appropriate rescaling factor most often involves training a separate network for many different factors and comparing the performance of each model. The computational burden of these models means that in practice it is rarely done, and when done only a few different scaling factors are considered. In this work, we present a hypernetwork strategy that can be used to easily and rapidly generate the Pareto frontier for the trade-off between accuracy and efficiency as the rescaling factor varies. We show how to train a single hypernetwork that generates CNN parameters conditioned on a rescaling factor. This enables a user to quickly choose a rescaling factor that appropriately balances accuracy and computational efficiency for their particular needs. We focus on image segmentation tasks, and demonstrate the value of this approach across various domains. We also find that, for a given rescaling factor, our single hypernetwork outperforms CNNs trained with fixed rescaling factors.


page 20

page 22

page 23


Towards integrating spatial localization in convolutional neural networks for brain image segmentation

Semantic segmentation is an established while rapidly evolving field in ...

Image Complexity Guided Network Compression for Biomedical Image Segmentation

Compression is a standard procedure for making convolutional neural netw...

CC-Net: Image Complexity Guided Network Compression for Biomedical Image Segmentation

Convolutional neural networks (CNNs) for biomedical image analysis are o...

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Interactive single-image segmentation is ubiquitous in the scientific an...

Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

The usage of convolutional neural networks (CNNs) for unsupervised image...

Post-Train Adaptive U-Net for Image Segmentation

Typical neural network architectures used for image segmentation cannot ...

Nonlinear Markov Random Fields Learned via Backpropagation

Although convolutional neural networks (CNNs) currently dominate competi...

Please sign up or login with your details

Forgot password? Click here to reset