Preserving details in semantics-aware context for scene parsing

Ma, Shuai; Pang, Yanwei; Pan, Jing; Shao, Ling

doi:10.1007/s11432-019-2738-y

Cited by 17 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, current segmentation methods are roughly categorized into three classes according to the measures which they adopt to diversify the sources of semantic information Multi-scale inputs: The motivation behind this kind of methods is to make the segmentation network adapt to objects with varying scales by training the network with multiple rescaled input images [4], [5]. Though this kind of methods do not explicitly increase the number of the receptive fields, the effect of resampling input images is equivalent to simultaneously probing the input images with several kernels with different sizes.…”

Section: Related Workmentioning

confidence: 99%

Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation

Lian

Pang

Han

et al. 2021

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Atrous Spatial Pyramid Pooling (ASPP) is a module that can collect semantic information distributed in different scopes. However, because of the limited number of sampling ranges of ASPP, much valuable global features and contextual information cannot be sufficiently sampled, which degrades the representation ability of the segmentation network. Besides, due to the sparse distribution of the effective sampling points in the atrous convolution kernels of ASPP, large amount of local detail characteristics are easily discarded.

show abstract

Section: Related Workmentioning

confidence: 99%

Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation

Lian

Pang

Han

et al. 2021

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…To improve the information extraction of global context, Jie Jiang et al [2] proposed a novel global-guided selective context network (GSCNet) to select contextual information adaptively. Multi-scale feature fusion and enhancement network (MFFENet) [3], semantic consistency module [4], and attention residual block-embedded adversarial networks (AREANs) [5] can fuse global semantic information at multiple scales. For information extraction of local information features, Shiyu Liu et al [6] highlighted the strong correlation between depth and semantic information by introducing a built-in deep semantic coupling coding module that adaptively fuses RGB and depth features.…”

Section: Introductionmentioning

confidence: 99%

Global enhancement network underwater archaeology scene parsing method

Pan,

Jia,

Cai

2023

Robotica

View full text Add to dashboard Cite

Underwater archaeology is of great significance for historical and cultural transmission and preservation of underwater heritage, but it is also a challenging task. Underwater heritage is located in an environment with high sediment content, objects are mostly buried, and the water is turbid, resulting in some of the features of objects missing or blurred, making it difficult to accurately identify and understand the semantics of various objects in the scene. To tackle these issues, this paper proposes a global enhancement network (GENet) underwater scene parsing method. We introduce adaptive dilated convolution by adding an extra regression layer, which can automatically deduce adaptive dilated coefficients according to the different scene objects. In addition, considering the easy confusion in the process of fuzzy feature classification, an enhancement classification network is proposed to increase the difference between various types of probabilities by reducing the loss function. We verified the validity of the proposed model by conducting numerous experiments on the Underwater Shipwreck Scenes (USS) dataset. We achieve state-of-the-art performance compared to the current state-of-the-art algorithm under three different conditions: conventional, relic semi-buried, and turbidified water quality. The experimental results show that the proposed algorithm performs best in different situations. To verify the generalizability of the proposed algorithm, we conducted comparative experiments on the current publicly available Cityscapes, ADE20K, and the underwater dataset SUIM. The experimental results show that this paper achieves good performance on the public dataset, indicating that the proposed algorithm is generalizable.

show abstract

“…Owing to the presence of turbidity media in the atmosphere (such as haze, smoke, dust, and other particles), which can absorb and scatter light, quality reduction phenomena such as spectral distortion and spatial blurriness often occur in images, which introduces difficulties to processing tasks such as target detection [1], image segmentation [2] and advanced driver assistance system [3]. In addition, it is not feasible to capture both haze-free and hazy images in the same scene simultaneously for image dehazing algorithms.…”

Section: Introductionmentioning

confidence: 99%

Single image dehazing using generative adversarial networks based on an attention mechanism

Jia

Yan

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Most existing image dehazing methods rely on the solution of the atmospheric scattering model or supervised learning based on paired images. However, owing to incomplete prior knowledge and the lack of paired hazy and haze-free images of the same scenes as training samples, their performances for single image dehazing are unsatisfactory. Here, the authors present an unpaired image learning method based on the attention mechanism for single image dehazing problems. The method uses the constraint transfer learning ability and circulatory structure of CycleGAN to carry out an unsupervised image dehazing task for unpaired data. Considering the complexity of the haze distribution in actual imaging and human visual characteristics, the improved channel attention and domain attention mechanisms are integrated into the network to process different features and different regions non-uniformly. The experimental results show that the proposed method achieves good results on both synthetic datasets and real hazy images.

show abstract

Preserving details in semantics-aware context for scene parsing

Cited by 17 publications

References 43 publications

Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation

Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation

Global enhancement network underwater archaeology scene parsing method

Single image dehazing using generative adversarial networks based on an attention mechanism

Contact Info

Product

Resources

About