Edge-Aware Convolution Neural Network Based Salient Object Detection

Guan, Wenlong; Wang, Tiantian; Qi, Jinqing; Zhang, Lihe; Lu, Huchuan

doi:10.1109/lsp.2018.2881835

Cited by 57 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guan et. al [41] propose an edge detection stream to combine multiple side outputs together through concatenation and uses a fusion layer that a 1 × 1 convolution to get the unified output. With the edge information added, these above models achieve good performance in preserving the boundary of salient object.…”

Section: B Exploiting Edge Informationmentioning

confidence: 99%

Edge-Guided Non-Local Fully Convolutional Network for Salient Object Detection

et al. 2021

IEEE Trans. Circuits Syst. Video Technol.

107

View full text Add to dashboard Cite

Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCNbased methods still suffer from continuous striding and pooling operations leading to loss of spatial structure and blurred edges. To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edgeguided feature learning for accurate salient object detection. In a specific, we extract hierarchical global and local information in FCN to incorporate non-local features for effective feature representations. To preserve good boundaries of salient objects, we propose a guidance block to embed edge prior knowledge into hierarchical feature maps. The guidance block not only performs feature-wise manipulation but also spatial-wise transformation for effective edge embeddings. Our model is trained on the MSRA-B dataset and tested on five popular benchmark datasets. Comparing with the state-of-the-art methods, the proposed method achieves the best performance on all datasets.

show abstract

Section: B Exploiting Edge Informationmentioning

confidence: 99%

Edge-Guided Non-Local Fully Convolutional Network for Salient Object Detection

et al. 2021

IEEE Trans. Circuits Syst. Video Technol.

107

View full text Add to dashboard Cite

show abstract

“…Recently, a number of deep learning-based prefiltering approaches have been adopted for targeted coding optimization. These include denoising [29], [30], motion deblurring [31], [32], contrast enhancement [33], edge detection [34], [35], and so on. Another important topic is closely related to the analysis of video content semantics, for example, object instance, saliency attention, and texture distribution, and its application to intelligent video coding.…”

Section: O V E R V I E W O F D N N -B a S E D V I D E O P R E P Rmentioning

confidence: 99%

Advances in Video Compression System Using Deep Neural Network: A Review and Case Studies

Ding

Chen

et al. 2021

Proc. IEEE

View full text Add to dashboard Cite

Significant advances in video compression systems have been made in the past several decades to satisfy the near-exponential growth of Internet-scale video traffic. From the application perspective, we have identified three major functional blocks, including preprocessing, coding, and postprocessing, which have been continuously investigated to maximize the end-user quality of experience (QoE) under a limited bit rate budget. Recently, artificial intelligence (AI)-powered techniques have shown great potential to further increase the efficiency of the aforementioned functional blocks, both individually and jointly. In this article, we review recent technical advances in video compression systems extensively, with an emphasis on deep neural network (DNN)based approaches, and then present three comprehensive case studies. On preprocessing, we show a switchable texturebased video coding example that leverages DNN-based scene understanding to extract semantic areas for the improvement Manuscript

show abstract

“…In recent years, CNN have been successfully applied for saliency detection and have achieved substantial improvements over other methods due to their powerful feature representation abilities. In particular, various SOD methods [30]- [32] that are based on fully convolutional neural networks (FCN) have achieved accurate results. Guan et al [30] added edge features as complementary information for SOD.…”

Section: Related Workmentioning

confidence: 99%

“…In particular, various SOD methods [30]- [32] that are based on fully convolutional neural networks (FCN) have achieved accurate results. Guan et al [30] added edge features as complementary information for SOD. Huang et al [31] leveraged a multiscale iteration of a CNN with two complementary subnets on different spatial scales, which combined the predictions of the two subnets to generate a more accurate boundary.…”

Section: Related Workmentioning

confidence: 99%

Salient Object Detection: An Accurate and Efficient Method for Complex Shape Objects

Qiao¹,

Zhou

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Deep learning-based salient object detection (SOD) methods have made great progress in recent years. However, most deep learning-based methods suffer from coarse object boundaries and expensive computations, especially in detecting objects with complex shapes. This paper presents an accurate and efficient SOD method that is based on a novel double-branch network that includes a body branch and an edge branch. To obtain an accurate edge, an edge profile enhancement module (EPEM) is embedded in the edge branch. In addition, a fusion feedback module (FFM) is embedded to integrate features from the two branches. To address the problem of expensive computations, channel attention module (CAM) is included to restrain redundant feature channels. Thus, the speed of the inference step can be improved with little reduction in the boundary accuracy. Experimental results on 9 datasets demonstrate that the proposed method performs favorably against 8 state-of-the-art methods in terms of both accuracy and efficiency. Additionally, our method achieves excellent detection results for objects with complex shapes.INDEX TERMS salient object detection, complex shape object, edge profile enhancement module, channel attention module, fusion feedback module

show abstract

Edge-Aware Convolution Neural Network Based Salient Object Detection

Cited by 57 publications

References 24 publications

Edge-Guided Non-Local Fully Convolutional Network for Salient Object Detection

Edge-Guided Non-Local Fully Convolutional Network for Salient Object Detection

Advances in Video Compression System Using Deep Neural Network: A Review and Case Studies

Salient Object Detection: An Accurate and Efficient Method for Complex Shape Objects

Contact Info

Product

Resources

About