Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

By Zhe Wu, Li Su, Qingming Huang. IEEE International Conference on Computer Vision, 2019

381 citations recorded by the source corpus.

Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://github.com/wuzhe71/SCAN.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/3bc945a59b3ff976ab3983dfdd754e18fbb62436

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

In Human-Computer Interaction

Citations in the corpus

Simultaneously Localize, Segment and Rank the Camouflaged Objects (2021, neutral): “CAMO CHAMELEON COD10K NC4K Method Sα ↑ F β ↑ E mean ξ ↑ M ↓ Sα ↑ F mean β ↑ E mean ξ ↑ M ↓ Sα ↑ F mean β ↑ E mean ξ ↑ M ↓ Sα ↑ F mean β ↑ E mean ξ ↑ M ↓ SCRN [53] 0.”
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 ”
Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images (2020, neutral): “a multi-scale strategy [58].”
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].”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “EGNet [41] SCRN [34] ECSSD DUTS DUT-O ECSSD DUTS DUT-O”
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, methodology): “SCRN [48], F(3)Net [46], ITSD [59], and it can indeed improve model performance.”
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-”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, background): “CPD [63]PoolNet [43]PiCANet [44]PAGRN [69]R3Net [14]Ours (w/o D) Ours (w/ D) Tab.”