DeepAI AI Chat
Log In Sign Up

Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks

by   Sérgio Pereira, et al.

Fully Convolutional Networks have been achieving remarkable results in image semantic segmentation, while being efficient. Such efficiency results from the capability of segmenting several voxels in a single forward pass. So, there is a direct spatial correspondence between a unit in a feature map and the voxel in the same location. In a convolutional layer, the kernel spans over all channels and extracts information from them. We observe that linear recombination of feature maps by increasing the number of channels followed by compression may enhance their discriminative power. Moreover, not all feature maps have the same relevance for the classes being predicted. In order to learn the inter-channel relationships and recalibrate the channels to suppress the less relevant ones, Squeeze and Excitation blocks were proposed in the context of image classification with Convolutional Neural Networks. However, this is not well adapted for segmentation with Fully Convolutional Networks since they segment several objects simultaneously, hence a feature map may contain relevant information only in some locations. In this paper, we propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with Fully Convolutional Networks - the SegSE block. Feature maps are recalibrated by considering the cross-channel information together with spatial relevance. Experimental results indicate that Recombination and Recalibration improve the results of a competitive baseline, and generalize across three different problems: brain tumor segmentation, stroke penumbra estimation, and ischemic stroke lesion outcome prediction. The obtained results are competitive or outperform the state of the art in the three applications.


page 1

page 7

page 9


Fully Convolutional Networks for Semantic Segmentation

Convolutional networks are powerful visual models that yield hierarchies...

Delving Deeper into Anti-aliasing in ConvNets

Aliasing refers to the phenomenon that high frequency signals degenerate...

InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation

We present a novel, parameter-efficient and practical fully convolutiona...

Dilated Residual Networks

Convolutional networks for image classification progressively reduce res...

semantic segmentation for urban planning maps based on u-net

The automatic digitizing of paper maps is a significant and challenging ...

Spatially Attentive Output Layer for Image Classification

Most convolutional neural networks (CNNs) for image classification use a...