Salient Object Detection With Pyramid Attention and Salient Edges

By Wenguan Wang, Shuyang Zhao, Jianbing Shen, Steven C. H. Hoi, Ali Borji. Computer Vision and Pattern Recognition, 2019

477 citations recorded by the source corpus.

This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions. The first is the exploitation of an essential pyramid attention structure for salient object detection. This enables the network to concentrate more on salient regions while considering multi-scale saliency information. Such a stacked attention design provides a powerful tool to efficiently improve the representation ability of the corresponding network layer with an enlarged receptive field. The second contribution lies in the emphasis on the importance of salient edges. Salient edge information offers a strong cue to better segment salient objects and refine object boundaries. To this end, our model is equipped with a salient edge detection module, which is learned for precise salient boundary estimation. This encourages better edge-preserving salient object segmentation. Exhaustive experiments confirm that the proposed pyramid attention and salient edges are effective for salient object detection. We show that our deep saliency model outperforms state-of-the-art approaches for several benchmarks with a fast processing speed (25fps on one GPU).

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a6376cb4353eafba8284be593029a8ef309ec271

How researchers see this paper

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

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

LayerCAM: Exploring Hierarchical Class Activation Maps for Localization (2021, background): “Many vision tasks, such as the challenging object detection task [37], [38], saliency object detection task [39], [40], and semantic segmentation task [41], [42], have beneﬁted from the semantic knowledge of different feature hierarchies.”
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, methodology): “We compare our model with 16 existing saliency detection models, including 10 nearly real-time models, such as RFCN [32], Amulet [45], UCF [46], NLDF [24], CKT [18], BMP [44], PCA [22], PAGE [35], DSS [12], EGNet [48] and 6 real-time models, such as RA [3], AFNet [8], BASNet [26], CPD [37], PoolNet ”
Camouflaged Object Detection (2020, background): “…similarities between the target object and the background make COD far more challenging than the traditional salient object detection [1,5,17,25,62– 66, In addition to its scientiﬁc value, COD is also beneﬁcial for applications in the ﬁelds of computer vision (for search-and-rescue work, or rare…”
Exploring Cross-Image Pixel Contrast for Semantic Segmentation (2021, unknown): “A main group of follow-up effort attempts to aggregate multiple pixels to explicitly model context, for example, utilizing different sizes of convolutional/pooling kernels or dilation rates to gather multi-scale visual cues [80, 84, 8, 9], building image pyramids to extract context from multi-resolu”
Multi-Scale Interactive Network for Salient Object Detection (2020, methodology): “Following most existing state-of-the-art methods [30, 27, 41, 34, 37, 46, 48, 20, 53, 32, 42, 56], we use the DUTS-0 TR [31] as the training dataset.”
Salient Object Detection via Integrity Learning (2021, methodology): “We compare our proposed approach with 16 very recent stateof-the-art SOD methods, including BMPM [114], PiCANet [23], R3Net [95], RAS [96], PAGE [97], AFNet [98], BASNet [85], CPD [99], PoolNet [27], SIBA [100], EGNet [18], SCRN [101], F3Net [102], MINet [19], ITSD [103] and GateNet [104].”
RGB-D salient object detection: A survey (2020, background): “Although significant progress has made in the SOD field over the past several years [50, 73, 73, 77, 119, 136, 142, 150, 151, 157, 168, 169, 174, 176], there is still room for improvement under challenging factors such as complicated background or different lighting conditions”
Enriched Feature Guided Refinement Network for Object Detection (2019, background): “Convolutional neural networks (CNNs) [36, 18, 9, 38, 29, 37] based object detectors [14, 15, 32, 17, 33, 8, 27, 2] have shown outstanding results in recent years.”
Revisiting Video Saliency Prediction in the Deep Learning Era (2021, background): “A related topic is salient object detection [63], [64] that uniformly highlights salient object regions in images [65], [66], [67], [68], [69], videos [70], [71], [72], [73], image/video groups [74], or RGBD data [75], [76].”
Attentional Feature Fusion (2020, background): “The second type, which is also referred to as multi-scale spatial attention, aggregates feature contexts by convolutional kernels of different sizes [20] or from a pyramid [20, 44] inside the attention module .”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, methodology): “son of F-measure curves over different thresholds. As the ﬁgure shows, F3Net achieves the best performance on all datasets. al. 2018), PiCA-R (Liu, Han, and Yang 2018), DGRL (Wang et al. 2018), TDBU (Wang et al. 2019b), PoolNet (Liu et al. 2019), PAGE (Wang et al. 2019c), RAS (Chen et al. 2018) and ”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “Some saliency methods [7,70,57] employ attention networks.”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “In addition to saliency masks, edge label is also introduced to SOD in [23, 34, 31, 20, 39, 42] to assist the generation of saliency maps.”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, methodology): “(i) Deep-based RGB-D SOD methods are still underexplored: Despite more than one hundred papers on RGB SOD models being published since 2015 [15,61,64,65,69], there are only a few deep learning-based works focusing on RGB-D SOD.”
PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection (2020, unknown): “Inspiredby[42],[43],thepyramidfea-turefusion(PFF)modulewasproposedinthisarticleasshownin Fig.”