Adaptive Context Network for Scene Parsing

Fu, Jun; Liu, Jing; Wang, Yuhang; Li, Yong; Bao, Yongjun; Tang, Jinhui; Lu, Hanqing

doi:10.1109/iccv.2019.00685

Cited by 141 publications

(77 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to obtain global contextual affinity, we should firstly aggregate global information for generating global contextual feature representations. It has been proven that the global average pooling (GAP) can effectively capture global contextual information without complex computational redundancy 43,44,46,47 . Therefore, the feature map B is fed into a GAP layer to generate a global representation

g \in {boldR}^{C \times 1 \times 1}

.…”

Section: Methodsmentioning

confidence: 99%

DCANet: Dual contextual affinity network for mass segmentation in whole mammograms

Lou

Meng

et al. 2021

Medical Physics

View full text Add to dashboard Cite

Purpose Breast mass segmentation in mammograms remains a crucial yet challenging topic in computer‐aided diagnosis systems. Existing algorithms mainly used mass‐centered patches to achieve mass segmentation, which is time‐consuming and unstable in clinical diagnosis. Therefore, we aim to directly perform fully automated mass segmentation in whole mammograms with deep learning solutions. Methods In this work, we propose a novel dual contextual affinity network (a.k.a., DCANet) for mass segmentation in whole mammograms. Based on the encoder–decoder structure, two lightweight yet effective contextual affinity modules including the global‐guided affinity module (GAM) and the local‐guided affinity module (LAM) are proposed. The former aggregates the features integrated by all positions and captures long‐range contextual dependencies, aiming to enhance the feature representations of homogeneous regions. The latter emphasizes semantic information around each position and exploits contextual affinity based on the local field‐of‐view, aiming to improve the indistinction among heterogeneous regions. Results The proposed DCANet is greatly demonstrated on two public mammographic databases including the DDSM and the INbreast, achieving the Dice similarity coefficient (DSC) of 85.95% and 84.65%, respectively. Both segmentation performance and computational efficiency outperform the current state‐of‐the‐art methods. Conclusion According to extensive qualitative and quantitative analyses, we believe that the proposed fully automated approach has sufficient robustness to provide fast and accurate diagnoses for possible clinical breast mass segmentation.

show abstract

g \in {boldR}^{C \times 1 \times 1}

.…”

Section: Methodsmentioning

confidence: 99%

DCANet: Dual contextual affinity network for mass segmentation in whole mammograms

Lou

Meng

et al. 2021

Medical Physics

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)

239

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

“…These methods rely on the last layer for scaling features which has reduced receptive field. To counter this challenge [36] and [37] leverage intermediate features to understand scaling along with last layer. These techniques use dilation and pooling, which result in patterned scaling.…”

Section: Related Workmentioning

confidence: 99%

End to End Segmentation of Canola Field Images Using Dilated U-Net

2021

View full text Add to dashboard Cite

Semantic segmentation is used in many fields like agriculture, medical imaging, and autonomous driving. The paper proposes an end to end solution for efficient weeds and crop segmentation in field environment application. The crop/weeds segmented output is utilized to generate a decision map for variable rate fertilizer and herbicide application. Currently available models are memory expensive and do not have real time performance unless enough computational power is accessible in field. We use Maximum Likelihood Classification (MLC) and image processing techniques to label field images in three classes; background, crop, and weeds. This data is processed through our modified U-Net, which improves the semantic accuracy with reduced memory cost. We train our model with DICE loss and compare the results with state of the art. We achieve 89.12% mean Intersection Over Union (mIOU) with 86.11%, 82.99%, and 98.23% individual IOU for crop, weeds, and background, respectively. Our proposed model uses only 15M parameters which are 57M less than the state-of-the-art models with a compromise of 1% mIOU score.

show abstract

Adaptive Context Network for Scene Parsing

Cited by 141 publications

References 35 publications

DCANet: Dual contextual affinity network for mass segmentation in whole mammograms

DCANet: Dual contextual affinity network for mass segmentation in whole mammograms

Boundary-Aware Feature Propagation for Scene Segmentation

End to End Segmentation of Canola Field Images Using Dilated U-Net

Contact Info

Product

Resources

About