Superpixel Segmentation With Fully Convolutional Networks

Yang, Fengting; Sun, Qing; Jin, Hailin; Zhou, Zihan

doi:10.1109/cvpr42600.2020.01398

Cited by 188 publications

(166 citation statements)

References 29 publications

Supporting

Mentioning

165

Contrasting

Order By: Relevance

“…Recently, deep-learning based superpixel segmentation methods are being increasingly researched, which fall under the category of supervised superpixel segmentation methods. In [15] the authors use a simple fully connected convolutional network to predict superpixels on an image grid. Then based on the predicted superpixels, they develop a high-resolution image generating down sampling/up sampling scheme for dense prediction tasks, in order to predict superpixels as well as disparities in stereo-images.…”

Section: Related Workmentioning

confidence: 99%

Iterative Boundaries Implicit Identification for Superpixels Segmentation: A Real-Time Approach

Bobbia¹,

Macwan²,

Benezeth³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Superpixel algorithms group visually coherent pixels and form an alternative representation of the regular structure of the pixel grid. This fundamental low-level computer vision preprocessing step greatly reduces the complexity of subsequent image processing tasks. However, most of the existing methods suffer from very high calculation costs which makes them quite unsuitable for time-sensitive applications. In this paper, we propose a new superpixel segmentation method, named IBIS for Iterative Boundaries implicit Identification for superpixels segmentation, that implicitly identifies the boundaries between superpixels and performs the segmentation using only a fraction of the pixels of the input image, thereby reducing the complexity and computation time. The results obtained during the experiments show that the segmentation quality of IBIS is comparable to that of state of the art methods with a computation time divided by a factor of 8 without parallelization of the processing for low resolution images (e.g., 320x240 pixels) as usually provided in public data sets. We also present and comprehensively evaluate the GPU variant of IBIS named IBIScuda that allows an optimal exploitation of the available resources considering the limited bandwidth between CPU and GPU memories.

show abstract

Section: Related Workmentioning

confidence: 99%

Iterative Boundaries Implicit Identification for Superpixels Segmentation: A Real-Time Approach

Bobbia¹,

Macwan²,

Benezeth³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In experiment, we compare our method with some state-ofthe-art methods, including SLIC [10], TPS [9], FCN [14] and SSN [13].…”

Section: Qualitative and Quantitative Comparisonmentioning

confidence: 99%

“…Superpixel sampling networks (SSN) [13] is proposed to generate deep feature by a deep neural network and to use a differentiable SLIC [10] to produce superpixel. Superpixel segmentation with fully convolutional network (FCN) [14] adopts an encoder-decoder model to generate the distance map between superpixel centers and pixels, directly generating superpixels with any other operations. Nowadays, dual cameras are widely used in autonomous vehicles and mobile phones.…”

Section: Introductionmentioning

confidence: 99%

Stereo Superpixel Segmentation Via Dual-Attention Fusion Networks

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Stereo image pairs can improve performance of many tasks benefiting from the additional information obtained from a second viewpoint when compared with single images. Existing superpixel segmentation algorithms for stereo images mostly adopt single images as input, and neglect the correspondence between the left and right views. In this work, we consider to exploit the depth information between stereo image pairs, and propose an end-to-end dual-attention fusion network for stereo images to generate parallax-consistency superpixels. We first utilize a deep convolution network to extract the deep features of stereo images. Then, to effectively utilize the additional information from the other view, features of the left and right views is integrated by a parallax attention and channel attention mechanism. Finally, the stereo superpixels are generated by a differentiable clustering algorithm, which is end-to-end trainable with deep learning networks. Comprehensive experimental results demonstrate that our method can outperform the state-of-the-art performance on the KITTI2015 and Cityscapes dataset.

show abstract

“…Hence, we propose a correlation context-driven method for sea fog detection in satellite imagery. First, a pixel-to-superpixel association map which assigns each pixel to its surrounding grids is obtained via a simple, yet effective fully convolutional network, following up on [12]. Then, superpixel feature maps are computed and fed into the downstream segmentation network for superpixel-level dense prediction.…”

Section: Introductionmentioning

confidence: 99%

A Correlation Context-Driven Method for Sea Fog Detection in Meteorological Satellite Imagery

Huang

Guo

et al. 2022

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Sea fog detection is a challenging and essential issue in satellite remote sensing. Although conventional threshold methods and deep learning methods can achieve pixel-level classification, it is difficult to distinguish ambiguous boundaries and thin structures from the background. Considering the correlations between neighbor pixels and the affinities between superpixels, a correlation context-driven method for sea fog detection is proposed in this letter, which mainly consists of a two-stage superpixel-based fully convolutional network (SFCNet), named SFCNet. A fully connected Conditional Random Field (CRF) is utilized to model the dependencies between pixels. To alleviate the problem of high cloud occlusion, an attentive Generative Adversarial Network (GAN) is implemented for image enhancement by exploiting contextual information. Experimental results demonstrate that our proposed method achieves 91.65% mIoU and obtains more refined segmentation results, performing well in detecting fogs in small, broken bits and weak contrast thin structures, as well as detects more obscured parts.

show abstract

Superpixel Segmentation With Fully Convolutional Networks

Cited by 188 publications

References 29 publications

Iterative Boundaries Implicit Identification for Superpixels Segmentation: A Real-Time Approach

Iterative Boundaries Implicit Identification for Superpixels Segmentation: A Real-Time Approach

Stereo Superpixel Segmentation Via Dual-Attention Fusion Networks

A Correlation Context-Driven Method for Sea Fog Detection in Meteorological Satellite Imagery

Contact Info

Product

Resources

About