Dynamic Multi-Scale Filters for Semantic Segmentation

He, Junjun; Deng, Zhongying; Qiao, Yu

doi:10.1109/iccv.2019.00366

Cited by 249 publications

(107 citation statements)

References 24 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…With respect to machine learning algorithms, DL requires more data and it is less transparent, making it difficult in clinical practice to retrieve from the trained algorithms some medical insights. Several categories of DL have been developed, including fully convolutional networks [ 15 ], encoder–decoder networks [ 16 ], multi-scale and pyramid network-based models [ 17 , 18 , 19 ], attention-based models [ 20 ], recurrent neural network-based models [ 21 ], and those based on generative and adversarial training [ 22 , 23 ]. For the lung segmentation task, several deep learning-based methods have been proposed (e.g., [ 6 , 11 , 24 , 25 , 26 ]).…”

Section: Introductionmentioning

confidence: 99%

Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies

et al. 2020

View full text Add to dashboard Cite

Background: The aim of this work is to identify an automatic, accurate, and fast deep learning segmentation approach, applied to the parenchyma, using a very small dataset of high-resolution computed tomography images of patients with idiopathic pulmonary fibrosis. In this way, we aim to enhance the methodology performed by healthcare operators in radiomics studies where operator-independent segmentation methods must be used to correctly identify the target and, consequently, the texture-based prediction model. Methods: Two deep learning models were investigated: (i) U-Net, already used in many biomedical image segmentation tasks, and (ii) E-Net, used for image segmentation tasks in self-driving cars, where hardware availability is limited and accurate segmentation is critical for user safety. Our small image dataset is composed of 42 studies of patients with idiopathic pulmonary fibrosis, of which only 32 were used for the training phase. We compared the performance of the two models in terms of the similarity of their segmentation outcome with the gold standard and in terms of their resources’ requirements. Results: E-Net can be used to obtain accurate (dice similarity coefficient = 95.90%), fast (20.32 s), and clinically acceptable segmentation of the lung region. Conclusions: We demonstrated that deep learning models can be efficiently applied to rapidly segment and quantify the parenchyma of patients with pulmonary fibrosis, without any radiologist supervision, in order to produce user-independent results.

show abstract

Section: Introductionmentioning

confidence: 99%

Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Scene segmentation (or scene parsing, semantic segmentation) is one of the fundamental problems in computer vision and has drawn lots of attentions. Recently, thanks to the great success of Convolutional Neural Networks (CNNs) in computer vision [42,68,71,52,25,72,27,80,26], lots of CNNs based segmentation works have been proposed and have achieved great progress [29,22,81,83,84,70,60]. For example, Long et al [54] introduce the fully convolutional networks (FCN) in which the fully connected layers in standard CNNs are transformed to convolutional layers.…”

Section: Related Work 21 Scene Segmentationmentioning

confidence: 99%

Boundary-Aware Feature Propagation for Scene Segmentation

Ding

Jiang

Liu

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

241

107

View full text Add to dashboard Cite

In this work, we address the challenging issue of scene segmentation. To increase the feature similarity of the same object while keeping the feature discrimination of different objects, we explore to propagate information throughout the image under the control of objects' boundaries. To this end, we first propose to learn the boundary as an additional semantic class to enable the network to be aware of the boundary layout. Then, we propose unidirectional acyclic graphs (UAGs) to model the function of undirected cyclic graphs (UCGs), which structurize the image via building graphic pixel-by-pixel connections, in an efficient and effective way. Furthermore, we propose a boundaryaware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image. The proposed BFP is capable of splitting the feature propagation into a set of semantic groups via building strong connections among the same segment region but weak connections between different segment regions. Without bells and whistles, our approach achieves new state-of-the-art segmentation performance on three challenging semantic segmentation datasets, i.e., PASCAL-Context, CamVid, and Cityscapes.

show abstract

“…Many works followed with techniques to produce high-quality segmentation [8][9][10][11], including better ways to extract features [12][13][14][15] and to take into account context [16,17]. Some recent works also proposed attention-based methods [18][19][20][21][22][23] and neural architecture search for image segmentation [24][25][26].…”

Section: Image Semantic Segmentationmentioning

confidence: 99%

Real-Time Segmentation Networks Should be Latency Aware

Courdier

Fleuret

2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

As scene segmentation systems reach visually accurate results, many recent papers focus on making these network architectures faster, smaller and more efficient. In particular, studies often aim at designing 'real-time' systems. Achieving this goal is particularly relevant in the context of real-time video understanding for autonomous vehicles, and robots. In this paper, we argue that the commonly used performance metric of mean Intersection over Union (mIoU) does not fully capture the information required to estimate the true performance of these networks when they operate in 'real-time'. We propose a change of objective in the segmentation task, and its associated metric that encapsulates this missing information in the following way: We propose to predict the future output segmentation map that will match the future input frame at the time when the network finishes the processing. We introduce the associated latency-aware metric, from which we can also determine a ranking. We perform latency timing experiments of some recent networks on different hardware and assess the performances of these networks on our proposed task. We propose improvements to scene segmentation networks to better perform on our task by using multi-frames input and increasing capacity in the initial convolutional layers.

show abstract

Dynamic Multi-Scale Filters for Semantic Segmentation

Cited by 249 publications

References 24 publications

Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies

Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies

Boundary-Aware Feature Propagation for Scene Segmentation

Real-Time Segmentation Networks Should be Latency Aware

Contact Info

Product

Resources

About