Pyramid Feature Attention Network for Saliency Detection

By Ting Zhao, Xiangqian Wu. Computer Vision and Pattern Recognition, 2019

691 citations recorded by the source corpus.

Saliency detection is one of the basic challenges in computer vision. Recently, CNNs are the most widely used and powerful techniques for saliency detection, in which feature maps from different layers are always integrated without distinction. However, instinctively, the different feature maps of CNNs and the different features in the same maps should play different roles in saliency detection. To address this problem, a novel CNN named pyramid feature attention network (PFAN) is proposed to enhance the high-level context features and the low-level spatial structural features. In the proposed PFAN, a context-aware pyramid feature extraction (CPFE) module is designed for multi-scale high-level feature maps to capture the rich context features. A channel-wise attention (CA) model and a spatial attention (SA) model are respectively applied to the CPFE feature maps and the low-level feature maps, and then fused to detect salient regions. Finally, an edge preservation loss is proposed to get the accurate boundaries of salient regions. The proposed PFAN is extensively evaluated on five benchmark datasets and the experimental results demonstrate that the proposed network outperforms the state-of-the-art approaches under different evaluation metrics.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bd63fef46192e7dd3eec6ab5ed0c2afa19556b3a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “Most existing models either use progressive decoder [67,53,70,57] or parallel decoder [12,72], as shown in Fig.”
Salient Object Detection via Integrity Learning (2021, background): “For instance, the recent works [24], [48], [49], [50], [51] used explicit boundary losses to guide the learning of boundary details.”
Deepstrip: High-Resolution Boundary Refinement (2020, background): “Recent decades have witnessed considerable effort to improve the boundary quality of an object that has been detected [41, 35, 32, 18, 37, 47, 16, 22] or segmented [11, 34, 24, 7].”
Attention mechanism-based CNN for facial expression recognition (2020, methodology): “The attention mechanism has been widely used in various computer vision tasks such as saliency detection [19], crowd counting [20] and facial expression recognition [42].”
Weakly-Supervised Salient Object Detection via Scribble Annotations (2020, methodology): “Models Metric DGRL UCF PiCANet R3Net NLDF MSNet CPD AFNet PFAN PAGRN BASNet SBF WSI WSS MNL MSW Ours [35] [53] [21] [5] [23] [40] [41] [8] [56] [54] [26] [48] [16] [34] [52] [47]”
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (2022, methodology): “For a fair comparison on SOD, the proposed model is retrained on DUTS [44] following the training strategies and techniques of [35,46,47,51,64].”
FcaNet: Frequency Channel Attention Networks (2020, methodology): “Besides these works, many methods try to extend the attention mechanism to speciﬁc tasks, like multi-label clas-siﬁcation [14], saliency detection [44], visual explanation [10], and super-resolution [43].”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, background): “Some studies like [100] have shown that deeper layers retain more semantic information for locating objects.”
Context-aware Cross-level Fusion Network for Camouflaged Object Detection (2021, neutral): “…PSPNet [Zhao et al., 2017], UNet++ [Zhou et al., 2018], PiCANet [Liu et al., 2018], MSRCNN [Huang et al., 2019a], BASNet [Qin et al., 2019], PFANet [Zhao and Wu, 2019], CPD [Wu et al., 2019], HTC [Chen et al., 2019], EGNet [Zhao et al., 2019], ANetSRM [Le et al., 2019], SINet [Fan et al., 2021a]…”
Camouflaged Object Detection (2020, methodology): “Compared with either the GOD [3,23,27,35,75,82] or the SOD [38,40,51,68,77, 78] models, SINet signiﬁcantly decreases the training time ( e.g ., SINet : 1 hour vs. EGNet: 48 hours) and achieves the SOTA performance on all datasets, showing that it is a promising solution for the COD problem.”
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, methodology): “Figure 6: Qualitative comparisons between different models: (c) UGTR, (d) SINet [12], (e) EGNet [59], (f) POOLNet [33], and (g) PFANet [60].”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “[42] directly built the edge loss with binary crossentropy to emphasize the importance of boundaries.”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, background): “(Zhao and Wu 2019) introduced the channel-wise attention and spatial attention to extract valuable features and suppress background noise.”
Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, background): “Pyramid Feature Attention extracts features from different levels of VGG [38].”
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation (2021, methodology): “Saliency detection (SD) methods generate the saliency map that distinguishes between the foreground and the background in an image via external saliency datasets with pixel-level annotations [18, 46, 51], or image-level annotations [39].”
RGB-D salient object detection: A survey (2020, background): “progress has been made in the SOD field over the past several years [30]–[36], [36]–[44], there is still room for improvement when faced with challenging factors, such as complicated background or different lighting conditions in the scenes.”