Boundary Information Progressive Guidance Network for Salient Object Detection

Yao, Zhaojian; Wang, Luping

doi:10.1109/tmm.2021.3115344

Cited by 14 publications

(9 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the saliency maps prediction branch, the binary cross‐entropy (BCE) and the intersection over union (IoU) loss functions [44, 49] are used to optimise the model. The BCE loss function can be expressed as:

{L}_{\text{BCE}}^{i}=-\sum\limits _{x,y}{G}_{x,y}\,\log \left({P}_{x,y}\right)+\left(1-{G}_{x,y}\right)\log \left(1-{P}_{x,y}\right)

where P x,y and G x,y denote the foreground probability value of the saliency maps and the ground truth (GT) maps, respectively.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…In the saliency maps prediction branch, the binary crossentropy (BCE) and the intersection over union (IoU) loss functions [44,49] are used to optimise the model. The BCE loss function can be expressed as:…”

Section: Loss Functionmentioning

confidence: 99%

“…[42] designed multi‐scale residual block capture information in different contexts to detect objects precisely. Recently, boundary feature guidance methods [44–48] have been proposed by many scholars, which can generate saliency maps more accurately using the boundary maps. Yao et al.…”

Section: Related Workmentioning

confidence: 99%

“…Yao et al. [44] built a boundary information progressive guidance model, which uses semantic and boundary features to progressively fuse as well as to generate complementary features for improving the quality of saliency maps. Zhou et al.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

RGB depth salient object detection via cross‐modal attention and boundary feature guidance

Meng,

Yuan,

Shi

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

RGB depth (RGB‐D) salient object detection (SOD) is a meaningful and challenging task, which has achieved good detection performance in dealing with simple scenes using convolutional neural networks, however, it cannot effectively handle scenes with complex contours of salient objects or similarly coloured salient objects and background. A novel end‐to‐end framework is proposed for RGB‐D SOD, which comprises of four main components: the cross‐modal attention feature enhancement (CMAFE) module, the multi‐level contextual feature interaction (MLCFI) module, the boundary feature extraction (BFE) module, and the multi‐level boundary attention guidance (MLBAG) module. The CMAFE module retains the more effective salient features by employing a dual‐attention mechanism to filter noise from two modalities. In the MLCFI module, a shuffle operation is used for high‐level and low‐level channels to promote cross‐channel information communication, and rich semantic information is extracted. The BFE module converts salient features into boundary features to generate boundary maps. The MLBAG module produces saliency maps by aggregating multi‐level boundary saliency maps to guide cross‐modal features in the decode stage. Extensive experiments are conducted on six public benchmark datasets, with the results demonstrating that the proposed model significantly outperforms 23 state‐of‐the‐art RGB‐D SOD models with regards to multiple evaluation metrics.

show abstract

{L}_{\text{BCE}}^{i}=-\sum\limits _{x,y}{G}_{x,y}\,\log \left({P}_{x,y}\right)+\left(1-{G}_{x,y}\right)\log \left(1-{P}_{x,y}\right)

where P x,y and G x,y denote the foreground probability value of the saliency maps and the ground truth (GT) maps, respectively.…”

Section: Proposed Methodsmentioning

confidence: 99%

Section: Loss Functionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

RGB depth salient object detection via cross‐modal attention and boundary feature guidance

Meng,

Yuan,

Shi

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Zhang et al [8] employ saliency cues and a multi-level fusion mechanism to detect salient objects. Yao et al [25] integrate the edge extraction module with the prediction network, yielding saliency maps with precise edge delineation. However, these SOD techniques are limited to RGB data and cannot be directly applied to hyperspectral data for HSOD.…”

Section: Related Work a Salient Object Detectionmentioning

confidence: 99%

Spectrum-Driven Mixed-Frequency Network for Hyperspectral Salient Object Detection

Liu,

Xu,

Chen

et al. 2024

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Hyperspectral salient object detection (HSOD) aims to detect spectrally salient objects in hyperspectral images (HSIs). However, existing methods inadequately utilize spectral information by either converting HSIs into false-color images or converging neural networks with clustering. We propose a novel approach that fully leverages the spectral characteristics by extracting two distinct frequency components from the spectrum: low-frequency Spectral Saliency and high-frequency Spectral Edge. The Spectral Saliency approximates the region of salient objects, while the Spectral Edge captures edge information of salient objects. These two complementary components, crucial for HSOD, are derived by computing from the inter-layer spectral angular distance of the Gaussian pyramid and the intra-neighborhood spectral angular gradients, respectively. To effectively utilize this dual-frequency information, we introduce a novel lightweight Spectrum-driven Mixed-frequency Network (SMN). SMN incorporates two parameter-free plug-and-play operators, namely Spectral Saliency Generator and Spectral Edge Operator, to extract the Spectral Saliency and Spectral Edge components from the input HSI independently. Subsequently, the Mixed-frequency Attention module, comprised of two frequencydependent heads, intelligently combines the embedded features of edge and saliency information, resulting in a mixed-frequency feature representation. Furthermore, a saliency-edge-aware decoder progressively scales up the mixed-frequency feature while preserving rich detail and saliency information for accurate salient object prediction. Extensive experiments conducted on the HS-SOD benchmark and our custom dataset HSOD-BIT demonstrate that our SMN outperforms state-of-the-art methods regarding HSOD performance. Code and dataset will be available at https://github.com/laprf/SMN.

show abstract

Bi-directional Interaction and Dense Aggregation Network for RGB-D Salient Object Detection

Yi,

Tang,

Bai

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Boundary Information Progressive Guidance Network for Salient Object Detection

Cited by 14 publications

References 66 publications

RGB depth salient object detection via cross‐modal attention and boundary feature guidance

RGB depth salient object detection via cross‐modal attention and boundary feature guidance

Spectrum-Driven Mixed-Frequency Network for Hyperspectral Salient Object Detection

Bi-directional Interaction and Dense Aggregation Network for RGB-D Salient Object Detection

Contact Info

Product

Resources

About