Progressive Attention Guided Recurrent Network for Salient Object Detection

By Xiaoning Zhang, Tiantian Wang, Jinqing Qi, Huchuan Lu, G. Wang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

582 citations recorded by the source corpus.

Effective convolutional features play an important role in saliency estimation but how to learn powerful features for saliency is still a challenging task. FCN-based methods directly apply multi-level convolutional features without distinction, which leads to sub-optimal results due to the distraction from redundant details. In this paper, we propose a novel attention guided network which selectively integrates multi-level contextual information in a progressive manner. Attentive features generated by our network can alleviate distraction of background thus achieve better performance. On the other hand, it is observed that most of existing algorithms conduct salient object detection by exploiting side-output features of the backbone feature extraction network. However, shallower layers of backbone network lack the ability to obtain global semantic information, which limits the effective feature learning. To address the problem, we introduce multi-path recurrent feedback to enhance our proposed progressive attention driven framework. Through multi-path recurrent connections, global semantic information from the top convolutional layer is transferred to shallower layers, which intrinsically refines the entire network. Experimental results on six benchmark datasets demonstrate that our algorithm performs favorably against the state-of-the-art approaches.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/297e7b1cd22ae14785a8e0b40339e41889294d25

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

A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019, methodology): “Image GT Ours PiCANet[24] DGRL[38] PAGR[46] SRM[37] Amulet[44] DSS[9] MSR[17] DCL[19]”
Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “The work in [115] extends the idea of RNN feature map refinement by introducing multi-path recurrency, which is essentially feedback connection from different depths of CNN. Deep learning has also been applied to detect salient objects in video.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “on (i.e., the inputs of the depth branch are or are not set to zeros). Methods NJU2K NLPR STERE DES LFSD SSD SIP [67] [32] [84] [35] [85] [86] [37] PiCANet [101] .847 .834 .868 .854 .761 .832 - PAGRN [48] .829 .844 .851 .858 .779 .793 - R3Net [81] .837 .798 .855 .847 .797 .815 - CPD [27] .894 .915 .”
U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection (2020, background): “(PAGRN) [56] develop a spatial and a channel-wise attention module to obtain the global information of each layer and propose a progressive attention guidance mechanism to reﬁne the saliency maps.”
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.”
Controllable Text-to-Image Generation (2019, background): “The attention mechanism has shown its efficiency in various research fields including image captioning [24, 30], machine translation [1], object detection [14, 29], and visual question answering [26].”
Salient Object Detection With Pyramid Attention and Salient Edges (2019, methodology): “SOD has been extensively studied in computer vision.”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, methodology): “We compare our method with 16 state-of-the-art ones, including 5 latest CNNs-based RGB-D methods: PCA [3], PDNet [48], MMCI [4], CTMF [18], DF [35]; 5 traditional RGB-D methods: MB [49], CDCP [50], NLPR [32], DES [8], DCMC [9]; 6 top ranking CNNs-based RGB methods: PiCANet [30], PAGRN [47], R(3)Net ”
Visual Saliency Transformer (2021, methodology): “To this end, they introduced various attention models [37, 80, 7], multi-scale feature integration methods [24, 49, 16, 43], and multi-task learning frameworks [67, 77, 82, 69, 25].”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “Some saliency methods [7,70,57] employ attention networks.”
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]”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, methodology): “(Zhang et al. 2018a) designed a bi-directional message passing model for better feature selection and integration.”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, methodology): “Then fully convolutional networks (FCNs) [23] based approaches [4, 15, 22, 24, 29, 30, 31, 35, 36, 37] further boost the development of salient object detection.”
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization (2021, background): “It has been widely adopted in many low-level and high-level vision tasks, such as denoising [5], [49], inpainting [50], super-resolution [51], [52], and object detection [53]–[56].”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, background): “Many SOD models have been developed under the assumption that the inputs are individual RGB/color images [21, 47, 66, 74–76] or sequences [56, 62, 67, 68].”
EGNet: Edge Guidance Network for Salient Object Detection (2019, methodology): “In this section, we compare our proposed EGNet with 15 previous state-of-the-art methods, including DCL [28], DSS [17,18], NLDF [35], MSR [26], ELD [13], DHS [32], RFCN [48], UCF [62], Amulet [61], PAGR [63], Pi-CANet [33], SRM [49], DGRL [52], RAS [3] and C2S [29].”
Pyramid Feature Attention Network for Saliency Detection (2019, methodology): “…0.0484 0.9249 0.0478 0.9200 0.0392 0.8806 0.0788 0.7740 0.0635 GRL[33] 0.8341 0.0509 0.9230 0.0446 0.9130 0.0377 0.8811 0.0799 0.7788 0.0632 PAGRN[45] 0.8546 0.0549 0.9237 0.0643 0.9170 0.0479 0.8690 0.0940 0.7709 0.0709 Amulet[43] 0.7773 0.0841 0.9138 0.0604 0.8968 0.0511 0.8619 0.0980 0.7428…”
Camouflaged Object Segmentation with Distraction Mining (2021, methodology): “Recurrent and iterative learning strategies are also employed to refine the saliency map progressively [64, 52].”