CVAug 14, 2020

Feedback Attention for Cell Image Segmentation

arXiv:2008.06474v18 citations
Originality Incremental advance
AI Analysis

This work addresses cell image segmentation for biomedical imaging, but it appears incremental as it builds on existing U-Net architectures with a novel attention component.

The paper tackled cell image segmentation by introducing a Feedback Attention mechanism inspired by human brain feedback processing, which improved results over conventional feedforward methods.

In this paper, we address cell image segmentation task by Feedback Attention mechanism like feedback processing. Unlike conventional neural network models of feedforward processing, we focused on the feedback processing in human brain and assumed that the network learns like a human by connecting feature maps from deep layers to shallow layers. We propose some Feedback Attentions which imitate human brain and feeds back the feature maps of output layer to close layer to the input. U-Net with Feedback Attention showed better result than the conventional methods using only feedforward processing.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes