Learning Deconvolution Network for Semantic Segmentation

Noh, Hyeonwoo; Hong, Seunghoon; Han, Bohyung

doi:10.1109/iccv.2015.178

Cited by 3,727 publications

(2,527 citation statements)

References 27 publications

Supporting

Mentioning

2,508

Contrasting

Unclassified

Order By: Relevance

“…Noh et al [42] use the conv-deconv architecture to do semantic segmentation, Rematas et al [44] use it to predict reflectance maps of objects. Zhao et al [43] develop a unified framework for supervised, unsupervised and semi-supervised learning by adding a reconstruction loss.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Stacked Hourglass Networks for Human Pose Estimation

Newell

Yang

Deng

2016

Lecture Notes in Computer Science

4,259

4,081

View full text Add to dashboard Cite

Abstract. This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods. Keywords: Human Pose Estimation

show abstract

Section: Related Workmentioning

confidence: 99%

“…The hourglass module before stacking is also related to conv-deconv and encoder-decoder architectures [42][43][44][45]. Noh et al [42] use the conv-deconv architecture to do semantic segmentation, Rematas et al [44] use it to predict reflectance maps of objects.…”

Section: Related Workmentioning

confidence: 99%

Stacked Hourglass Networks for Human Pose Estimation

Newell

Yang

Deng

2016

Lecture Notes in Computer Science

4,259

4,081

View full text Add to dashboard Cite

show abstract

“…As discussed in Ref. [3], a small receptive field may lead to inconsistent parsing results for large objects while a large receptive field may ignore small objects and classify them as background. Even if such extreme problems do not arise, unsuitable receptive fields can still impair performance.…”

Section: Introductionmentioning

confidence: 99%

Learning adaptive receptive fields for deep image parsing networks

et al. 2018

View full text Add to dashboard Cite

In this paper, we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks. Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the network's backbone and operates on feature maps. Feature maps are inflated or shrunk by the new layer, thereby changing the receptive fields in the following layers. By use of end-to-end training, the whole framework is data-driven, without laborious manual intervention. The proposed method is generic across datasets and different tasks. We have conducted extensive experiments on both general image parsing tasks, and face parsing tasks as concrete examples, to demonstrate the method's superior ability to regulate over manual designs.

show abstract

“…Unlike unsupervised learning, more than one features-other than color-can be extracted: line, shape, and texture, among others. The traditional deep learning methods such as deep convolutional neural networks (DCNN) [14] and [3], deep deconvolutional neural networks (DeCNN) [5], recurrent neural network, namely reSeg [15], and fully convolutional networks [4]. However, are all suffering from the accuracy performance issues.…”

Section: Introductionmentioning

confidence: 99%

Road Segmentation on Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

Panboonyuen¹,

Vateekul²,

Jitkajornwanich³

et al. 2017

Preprint

View full text Add to dashboard Cite

Abstract:Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction on remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve DCNN, a modern activation function, called exponential linear unit (ELU), is employed in our network resulting in a higher number of and yet more accurate extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as THEOS satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, the state-of-the-art object segmentation technique on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

show abstract

Learning Deconvolution Network for Semantic Segmentation

Cited by 3,727 publications

References 27 publications

Stacked Hourglass Networks for Human Pose Estimation

Stacked Hourglass Networks for Human Pose Estimation

Learning adaptive receptive fields for deep image parsing networks

Road Segmentation on Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

Contact Info

Product

Resources

About