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

arXiv: https://arxiv.org/abs/2006.11193 · HTML: https://mlsanity.com/paper/2006.11193/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2020.

## Built on by (most cited first, 13 of 13)

- [Cross-Modality Deep Feature Learning for Brain Tumor Segmentation](https://mlsanity.com/paper/2201.02356/) (2022)
- [ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos](https://mlsanity.com/paper/2109.12448/) (2021)
- [DeepPyramid: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos](https://mlsanity.com/paper/2207.01453/) (2022)
- [Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation](https://mlsanity.com/paper/2209.06107/) (2022)
- [Transformers-based architectures for stroke segmentation: A review](https://mlsanity.com/paper/2403.18637/) (2024)
- [Combining unsupervised and supervised learning for predicting the final stroke lesion](https://mlsanity.com/paper/2101.00489/) (2021)
- [Multi-stage Deep Layer Aggregation for Brain Tumor Segmentation](https://mlsanity.com/paper/2101.00490/) (2021)
- [Online Continual Learning via the Knowledge Invariant and Spread-out Properties](https://mlsanity.com/paper/2302.00858/) (2023)
- [3D Brainformer: 3D Fusion Transformer for Brain Tumor Segmentation](https://mlsanity.com/paper/2304.14508/) (2023)
- [DeepPyram: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos](https://mlsanity.com/paper/2109.05352/) (2021)
- [Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation](https://mlsanity.com/paper/2207.09162/) (2022)
- [Medical Image Analysis using Deep Relational Learning](https://mlsanity.com/paper/2303.16099/) (2023)
- [Multifractal Recalibration of Neural Networks for Medical Imaging Segmentation](https://mlsanity.com/paper/2512.02198/) (2025)

## Abstract (arXiv)

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.