Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Takikawa, Towaki; Acuna, David; Jampani, Varun; Fidler, Sanja

doi:10.48550/arxiv.1907.05740

Cited by 21 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Chen et al (2018) suggested well-organized architecture with combining encoder-decoder architecture and dilated convolution. Many subsequent methods that achieved state-of-the-art performance have followed this structure (Takikawa et al, 2019;Zhuang et al, 2018;Li et al, 2019). Zhu et al (2019) adopted DeeplabV3Plus (Chen et al, 2018) with WideResNet38 (Zagoruyko & Komodakis, 2016) as the backbone network.…”

Section: Related Workmentioning

confidence: 99%

Structured Consistency Loss for semi-supervised semantic segmentation

JongMok¹,

Jang

Park

2020

Preprint

View full text Add to dashboard Cite

The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant studies on semi-supervised semantic segmentation rely on pixel-wise classification, which does not reflect the structured nature of characteristics in prediction. We propose a structured consistency loss to address this limitation of extant studies. Structured consistency loss promotes consistency in inter-pixel similarity between teacher and student networks. Specifically, collaboration with CutMix optimizes the efficient performance of semi-supervised semantic segmentation with structured consistency loss by reducing computational burden dramatically. The superiority of proposed method is verified with the Cityscapes; The Cityscapes benchmark results with validation and with test data are 81.9 mIoU and 83.84 mIoU respectively. This ranks the first place on the pixel-level semantic labeling task of Cityscapes benchmark suite. To the best of our knowledge, we are the first to present the superiority of state-of-the-art semi-supervised learning in semantic segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

Structured Consistency Loss for semi-supervised semantic segmentation

JongMok¹,

Jang

Park

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The algorithm selected is the Gated-Shaped CNN (GSCNN) proposed by Takikawa et al (2019) to perform semantic segmentation on urban scenes from the CityScape dataset (Cordts et al, 2016). Its power lies in the fact that it simultaneously conducts contact detection, and semantic segmentation.…”

Section: Segmentation With Gated Shape Cnnmentioning

confidence: 99%

Predictive Geological Mapping with Convolution Neural Network Using Statistical Data Augmentation on a 3D Model

Cedou¹,

Erwan²,

Blouin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Airborne magnetic data are commonly processed and interpreted to produce preliminary geological maps. Machine learning has the potential to partly fulfill this task rapidly and objectively, as geological mapping is comparable to a semantic segmentation problem that can be solved with a convolutional neural network. Because this method requires a high-quality dataset, we developed a data augmentation workflow that uses a 3D geological and petrophysical (magnetic susceptibility) model as input. The workflow uses soft-constrained Multi-Point Statistics, to create many synthetic 3D geological models, and Sequential Gaussian Simulation algorithms, to populate the models with the appropriate magnetic distribution. Then, forward modeling is used to compute the airborne magnetic responses of the synthetic models, which are associated with their counterpart surficial lithologies. We applied this workflow on a 3D model of the geology and magnetic susceptibility of the Malartic Mine area to obtain a large airborne magnetic synthetic dataset, associated with surficial lithologies, and perform segmentation. A Gated Shape Convolutional Neural Network algorithm was trained on this synthetic dataset to perform geological mapping of the synthetic airborne magnetic data and detect lithological contacts. The algorithm also provides attention maps highlighting the structures at different scales, and clustering was applied to its high-level features to do a semi-supervised segmentation of the area. The validation conducted on a portion of the synthetic dataset shows that the methodology is suitable to segment the surficial geology using airborne magnetic data. We also used transfer learning to test the trained model on measured magnetic data from adjacent areas, without re-training. The clustering shows a good segmentation of the magnetic anomalies into a pertinent geological map in these areas. Moreover, the first attention map isolates the structures at low scales and shows a pertinent representation of the original data. The quality of the results empirically validates our data augmentation method. Furthermore, it proves that using convolutional neural networks is pertinent for preliminary geological mapping. Thus, our method can be used in any area where a geological and petrophysical 3D model exists to train a deep learning algorithm and produce preliminary geological maps of good quality and new representations of the input data in any area sharing the same geological context, using airborne magnetic data. (github: https://github.com/MatthieuCed/GSCNN-apply-to-airborne-magnetic)

show abstract

“…In recent years, deep learning has emerged as an effective method for image recognition tasks like image classification [4,5], object detection [6,7] and image segmentation [8,9]. Especially, convolutional neural network (CNN) has become a powerful model for these tasks.…”

Section: Introductionmentioning

confidence: 99%

Increasing Shape Bias to Improve the Precision of Center Pivot Irrigation System Detection

et al. 2021

View full text Add to dashboard Cite

Irrigation is indispensable in agriculture. Center pivot irrigation systems are popular means of irrigation since they are water-efficient and labor-saving. Monitoring center pivot irrigation systems provides important information for the understanding of agricultural production, water resources consumption and environmental change. Deep learning has become an effective approach for object detection and semantic segmentation. Recent studies have shown that convolutional neural networks (CNNs) are prone to be texture-biased rather than shape-biased, and increasing shape bias can improve the robustness and performance of CNNs. In this study, a simple yet effective method was proposed to increase shape bias in object detection networks to improve the precision of center pivot irrigation system detection. We extracted edge images of training samples and integrated them into the training data to increase shape bias in the networks. With the proposed shape increasing training scheme, we evaluated and compared PVANET and YOLOv4. Experiments with the images in Mato Grosso have shown that both PVANET and YOLOv4 achieved improved performance, which demonstrated the validity of the proposed method.

show abstract

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Cited by 21 publications

References 40 publications

Structured Consistency Loss for semi-supervised semantic segmentation

Structured Consistency Loss for semi-supervised semantic segmentation

Predictive Geological Mapping with Convolution Neural Network Using Statistical Data Augmentation on a 3D Model

Increasing Shape Bias to Improve the Precision of Center Pivot Irrigation System Detection

Contact Info

Product

Resources

About