Attentive Feedback Network for Boundary-Aware Salient Object Detection

By Mengyang Feng, Huchuan Lu, Errui Ding. Computer Vision and Pattern Recognition, 2019

456 citations recorded by the source corpus.

Recent deep learning based salient object detection methods achieve gratifying performance built upon Fully Convolutional Neural Networks (FCNs). However, most of them have suffered from the boundary challenge. The state-of-the-art methods employ feature aggregation tech- nique and can precisely find out wherein the salient object, but they often fail to segment out the entire object with fine boundaries, especially those raised narrow stripes. So there is still a large room for improvement over the FCN based models. In this paper, we design the Attentive Feedback Modules (AFMs) to better explore the structure of objects. A Boundary-Enhanced Loss (BEL) is further employed for learning exquisite boundaries. Our proposed deep model produces satisfying results on the object boundaries and achieves state-of-the-art performance on five widely tested salient object detection benchmarks. The network is in a fully convolutional fashion running at a speed of 26 FPS and does not need any post-processing.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ecb7fd539c6b32c15ee52d112a8f5003f685124a

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

A Survey of Deep Learning-Based Object Detection (2019, background): “tion prediction to detect salient objects. Wang et al. [221] utilize recurrent fully convolutional networks and incorporate saliency prior knowledge for accurate salient object detection. Feng et al. [222] propose an attentive feedback module to better explore the structure of objects. Video salient”
Visual Saliency Transformer (2021, methodology): “For RGB SOD, we compare our VST with 12 state-of-theart RGB SOD models, including GateNet [84], CSF [20], LDF [69], MINet [49], ITSD [87], EGNet [82], TSPOANet [41], AFNet [17], PoolNet [35], CPD [70], BASNet [55], and PiCANet [37].”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “To demonstrate the effectiveness of the proposed method, 14 state-of-the-art SOD methods are introduced to compare, including BMPM [38], DGRL [28], R(3)Net [7], RAS [4], PiCA-R [21], AFNet [13], BASNet [23], CPD-R [33], EGNet-R [41], PAGE [31], TDBU [30], SCRN [34], SIBA [24] and PoolNet [20].”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, methodology): “To demonstrate the effectiveness of the proposed F 3 Net, we compare it against 12 state-of-the-art SOD algorithms, including AFNet (Feng, Lu, and Ding 2019), BASNet (Qin et al. 2019), CPD-R (Wu, Su, and Huang 2019), BMPM (Zhang et al. 2018a), R 3 Net (Deng et Table 1: Performance comparison with 12”
Multi-Scale Interactive Network for Salient Object Detection (2020, methodology): “Some methods [23, 53, 4, 9, 40, 41, 27, 37] connect the features at the corresponding level in the encoder to the decoder via the transport layer (Fig.”
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, methodology): “[8] developed an Attentive Feedback Module (AFM) to refine the coarse predictions.”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, unknown): “, {64*224*224, 128*112*112, 256*56*56, 512*28*28, 512*14*14, 32*7*7, 32*14*14, 32*28*28, 32*56*56, 32*112*112, 32*224*224} on {Fi, i∈ [1,11]}, respectively.”
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].”
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]”