Open AccessPosted Content
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks
TL;DR: This paper introduces three variants of SE modules for image segmentation, and effectively incorporates these SE modules within three different state-of-the-art F-CNNs (DenseNet, SD-Net, U-Net) and observes consistent improvement of performance across all architectures, while minimally effecting model complexity.
read more
Abstract: Fully convolutional neural networks (F-CNNs) have set the state-of-the-art in image segmentation for a plethora of applications. Architectural innovations within F-CNNs have mainly focused on improving spatial encoding or network connectivity to aid gradient flow. In this paper, we explore an alternate direction of recalibrating the feature maps adaptively, to boost meaningful features, while suppressing weak ones. We draw inspiration from the recently proposed squeeze & excitation (SE) module for channel recalibration of feature maps for image classification. Towards this end, we introduce three variants of SE modules for image segmentation, (i) squeezing spatially and exciting channel-wise (cSE), (ii) squeezing channel-wise and exciting spatially (sSE) and (iii) concurrent spatial and channel squeeze & excitation (scSE). We effectively incorporate these SE modules within three different state-of-the-art F-CNNs (DenseNet, SD-Net, U-Net) and observe consistent improvement of performance across all architectures, while minimally effecting model complexity. Evaluations are performed on two challenging applications: whole brain segmentation on MRI scans (Multi-Atlas Labelling Challenge Dataset) and organ segmentation on whole body contrast enhanced CT scans (Visceral Dataset).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Fig. 1: Illustration of network architecture with squeeze & excitation (SE) blocks. (a) The proposed integration of SE blocks within F-CNN. (b-d) The architectural design of cSE, sSE and scSE blocks, respectively, for recalibrating feature map U. 
Table 1: Mean and standard deviation of the global Dice scores for the different FCNN models without and with cSE, sSE and scSE blocks on both datasets. 
Fig. 2: Boxplot of Dice scores for all brain structures on the left hemisphere (due to space constraints), using DenseNets on MALC dataset, without and with proposed cSE, sSE, scSE blocks. Grey and white matter are abbreviated as GM and WM, respectively. 
Fig. 4: Input scan, ground truth annotations, DenseNet segmentation and DenseNet+scSE segmentation for both whole-brain MRI T1 (a-d) and whole-body ceCT (e-h) are shown. ROIs are indicated by white box and red arrow highlighting regions where the scSE block improved the segmentation, for both applications. 
Fig. 3: Structure-wise Dice performance of DenseNets on Visceral dataset, without and with proposed cSE, sSE, scSE blocks. Left and right are indicated as L. and R. Psoas major muscle is abbreviated as PM.
Citations
The Change You Want to See (Now in 3D)
Ragav Sachdeva,A. Zisserman +1 more
TL;DR: This work contributes a change detection model that is trained entirely on synthetic data and is class-agnostic, yet it is performant out-of-the-box on real world images without requiring fine-tuning.
A Novel Carbon Stocking Estimation Through Continuous Catalog Learning
Dror Haor,Hagit Liven,Mira Barshai,E. Sela,Gordon Smith,Yakir Preisler +5 more
- 27 Oct 2023
TL;DR: A novel carbon stocking estimation method using continuous learning and high-resolution imagery data improves accuracy and provides valuable insights into diverse forest types.
Enhancing Robot Learning through Learned Human-Attention Feature Maps
Daniel Scheuchenstuhl,Stefan Ulmer,Felix Resch,Luigi Berducci,Radu Grosu +4 more
TL;DR: A novel approach to model and emulate the human attention with an approximate prediction model and feed it as a structured auxiliary feature map into downstream learning tasks to enhance efficiency and robustness of the learning process in robotics.
A multi-focus image fusion network combining dilated convolution with learnable spacings and residual dense network
Jidong Fang,Xinglin Ning,Taiyong Mao,Mengting Zhang,Yuefeng Zhao,Shaohai Hu,Jingjing Wang +6 more
Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images
Yao Zhang,Jiawei Yang,Yang Liu,Jiang Tian,Siyun Wang,Cheng Zhong,Zhongchao Shi,Yan Zhang,Zhiqiang He +8 more
TL;DR: A Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low- and high-level features embedded in FCN to segment liver tumor and can effectively model the multi-level correlation from both semantic and spatial dimensions is proposed.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Fully convolutional networks for semantic segmentation
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- 07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Related Papers (5)
Jie Hu,Li Shen,Samuel Albanie,Gang Sun,Enhua Wu +4 more
- 18 Jun 2018
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- 07 Jun 2015
Hengshuang Zhao,Jianping Shi,Xiaojuan Qi,Xiaogang Wang,Jiaya Jia +4 more
- 21 Jul 2017