Scene Segmentation With Dual Relation-Aware Attention Network

Fu, Jun; Liu, Jing; Jiang, Jie; Li, Yong; Bao, Yongjun; Lu, Hanqing

doi:10.1109/tnnls.2020.3006524

Cited by 212 publications

(108 citation statements)

References 47 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…Cao et al [28] proposed a global context network (GcNet) to capture long-range dependencies, which is based on the non-local neural networks [27] (NL). Dual-Attention [20] learns global context information in spatial and channel dimensions, without being constrained by the receptive field. Although CBAM [21] cannot utilize global context information, it is a lightweight model and can focus on locally relevant features to extract salient features.…”

Section: Related Workmentioning

confidence: 99%

“…We use the max function and the mean function to calculate the maximum value and average value of each column of ⨂ , and the matric size of the result is adjusted to × . It is worth noting that Dual-attention [20] is used for scene segmentation tasks, and its purpose is to assign edge information of different objects to its category accurately. However, in the Re-id task, we need to deal with occlusion and appearance similarity.…”

Section: Channel Attention Model Of Gl-attentionmentioning

confidence: 99%

“…To study the effectiveness of the GL-Attention, we add GL-Attention to the baseline network (B). We choose some advanced attention models for comparison, including CBAM [21], Dual-attention [20], NL [27] and GcNet [28]. For the fairness of comparison, we reimplement these attention models on top of the baseline.…”

Section: Ablation Experimentsmentioning

confidence: 99%

See 2 more Smart Citations

A Discriminative Person Re-Identification Model With Global-Local Attention and Adaptive Weighted Rank List Loss

Gong

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: Channel Attention Model Of Gl-attentionmentioning

confidence: 99%

See 1 more Smart Citation

A Discriminative Person Re-Identification Model With Global-Local Attention and Adaptive Weighted Rank List Loss

Gong

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

“…A majority of popular learning methods for image semantic segmentation are mainly based on fully convolutional network (FCN) [ 3 ], which greatly improves the segmentation accuracy and is considered as the cornerstone of this research field [ 4 ]. Nowadays, researches are conducted successively to look for improved or new semantic segmentation algorithms [ 5 , 6 , 7 , 8 , 9 , 10 , 11 ]. A semi-supervised multilabel FCN for hierarchical object parsing of images is presented in [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

“…In the meanwhile, a global-and-local network architecture (GLNet) is proposed in [ 9 ] to incorporate global spatial information and dense local multi-scale context information, so as to model the relationship between objects in a scene. To efficiently exploit context, two types of attention modules are appended on the top of the dilated FCN in [ 8 ]. Furthermore, challenges of learning spatial context for the semantic segmentation are addressed by using the Deep Convolutional Neural Networks (DCNNs) in [ 10 ] and a novel approach superpixel-enhanced deep neural forest is proposed to target the blur on object boundaries caused by DCNN-based semantic segmentation methods in [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Post-Processing Method Based on a Weighted Composite Filter for Enhancing Semantic Segmentation Results

Cheng

Liu

2020

Sensors

View full text Add to dashboard Cite

Image semantic segmentation is one of the key problems in computer vision. Despite the enormous advances in applications, almost all the image semantic segmentation algorithms fail to achieve satisfactory segmentation results due to lack of sensitivity to details, or difficulty in evaluating the global similarity of pixels, or both. Posting-processing enhancement methods, as the outstandingly crucial means to ameliorate the above-mentioned inherent flaws of algorithms, are almost based on conditional random fields (CRFs). Inspired by CRFs, this paper proposes a novel post-processing enhancement framework with theoretical simplicity from the perspective of filtering, and a new weighted composite filter (WCF) is designed to enhance the segmentation masks in a unified framework. First, by adjusting the weight ratio, the WCF is decomposed into a local part and a global part. Secondly, a guided image filter is designed as the local filter, which can restore boundary information to present necessary details. Moreover, a minimum spanning tree (MST)-based filter is designed as the global filter to provide a natural measure of global pixel similarity for image matching. Thirdly, a unified post-processing enhancement framework, including selection and normalization, WCF and argmax, is designed. Finally, the effectiveness and superiority of the proposed method for enhancement, as well as its range of applications, are verified through experiments.

show abstract

Potential roles of transformers in brain tumor diagnosis and treatment

Lan

Zou

Qin

et al. 2023

Brain-X

View full text Add to dashboard Cite

Brain tumor (BT) is one of many malignancies that have substantially enhanced global human morbidity and mortality rates. Early detection and characterization of glioma are essential for effective preventive strategies. Currently, the use of Transformers, a deep learning model for BT diagnosis and treatment, is attracting significant attention. The transformer self‐attention mechanism automatically learns the associations between input data for efficient processing and analysis. Research indicates that Transformers could play an essential role in the BT segmentation of magnetic resonance imaging (MRI) images, the MRI and histopathology‐based grading of brain cancer, BT molecular expression prediction, the classification of primary brain metastasis sites, voxel‐level dose and BT radiotherapy outcome prediction, synergistic prediction, and the pathway deconvolution of drug combinations. In this review, the feasibility, accuracy, and applicability of various algorithms are systematically analyzed and their prospects are discussed. Overall, this review aimed to discuss and provide an overview of the increasing applications of Transformers in real‐time BT detection and therapy, indicating their broad prospects and potential. In the future, Transformers are expected to be increasingly used for the diagnosis and subsequent treatment of BT because of the continuous development and improvement of Transformer‐based deep learning technology. However, more work is required to investigate their properties for anomaly detection, medical image classification, network design development, and application to other medical data.

show abstract

Scene Segmentation With Dual Relation-Aware Attention Network

Cited by 212 publications

References 47 publications

A Discriminative Person Re-Identification Model With Global-Local Attention and Adaptive Weighted Rank List Loss

A Discriminative Person Re-Identification Model With Global-Local Attention and Adaptive Weighted Rank List Loss

A Novel Post-Processing Method Based on a Weighted Composite Filter for Enhancing Semantic Segmentation Results

Potential roles of transformers in brain tumor diagnosis and treatment

Contact Info

Product

Resources

About