Mining self-similarity: Label super-resolution with epitomic representations
This work addresses the need for efficient and accurate label super-resolution in fields like remote sensing and medical imaging, offering a novel alternative to deep learning methods.
The paper tackled the problem of semantic segmentation and label super-resolution by proposing a new training algorithm for patch-based epitomic models, achieving superior performance over state-of-the-art deep convolutional neural networks, as demonstrated on land cover mapping and medical image analysis tasks.
We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which uses deep convolutional neural networks. We derive a new training algorithm for epitomes which allows, for the first time, learning from very large data sets and derive a label super-resolution algorithm as a statistical inference algorithm over epitomic representations. We illustrate our methods on land cover mapping and medical image analysis tasks.