PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection

By Nian Liu, Junwei Han, Ming-Hsuan Yang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017

808 citations recorded by the source corpus.

Contexts play an important role in the saliency detection task. However, given a context region, not all contextual information is helpful for the final task. In this paper, we propose a novel pixel-wise contextual attention network, i.e., the PiCANet, to learn to selectively attend to informative context locations for each pixel. Specifically, for each pixel, it can generate an attention map in which each attention weight corresponds to the contextual relevance at each context location. An attended contextual feature can then be constructed by selectively aggregating the contextual information. We formulate the proposed PiCANet in both global and local forms to attend to global and local contexts, respectively. Both models are fully differentiable and can be embedded into CNNs for joint training. We also incorporate the proposed models with the U-Net architecture to detect salient objects. Extensive experiments show that the proposed PiCANets can consistently improve saliency detection performance. The global and local PiCANets facilitate learning global contrast and homogeneousness, respectively. As a result, our saliency model can detect salient objects more accurately and uniformly, thus performing favorably against the state-of-the-art methods.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/557412c5aee48fb10f97fc95a4e097e40f10700d

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

Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, background): “Pixel-wise Contextual Attention: (PiCANet) [55] aims to learn accurate saliency detection.”
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (2019, methodology): “Many works [9, 17, 20, 21, 25, 41, 42] follow this strategy and precisely segment salient objects.”
Global Context-Aware Progressive Aggregation Network for Salient Object Detection (2020, positive): “We compare the proposed model with 12 state-of-the-art methods, including Amulet (Zhang et al. 2017), C2S (Li et al. 2018), RANet (Chen et al. 2018), PAGR (Zhang et al. 2018b), PiCANet-R (Liu, Han, and Yang 2018), DGRL (Wang et al. 2018), R 3 Net (Deng et al. 2018), BMPM (Zhang et al. 2018a), RADF (”
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 ”
Salient Object Detection With Pyramid Attention and Salient Edges (2019, methodology): “Only a few very recent methods for SOD [56, 27, 7] employ attention networks.”
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, methodology): “F-score and FPS comparisons of our ITSD with AFNet [8], PCA [22], Amulet [45], EGNet [48], CKT [18], CTLoss [4], NLDF [24], PoolNet [21], PAGE [35] and CPD [37] on DUTS-TE dataset [31].”
A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019, methodology): “When the edge branch is not incorporated, training only takes less than 6 hours on a training set of 5,000 images, which is quite faster than most of the previous methods [24, 43, 28, 44, 45, 9].”
Context-aware Cross-level Fusion Network for Camouflaged Object Detection (2021, neutral): “, 2018], PiCANet [Liu et al., 2018], MSRCNN [Huang et al.”
Camouflaged Object Detection (2020, methodology): “…0.075 2017 MaskRCNN [23] 0.643 0.778 0.518 0.099 0.574 0.715 0.430 0.151 0.613 0.748 0.402 0.080 2017 PSPNet [75] 0.773 0.758 0.555 0.085 0.663 0.659 0.455 0.139 0.678 0.680 0.377 0.080 2018 UNet++ [82] 0.695 0.762 0.501 0.094 0.599 0.653 0.392 0.149 0.623 0.672 0.350 0.086 2018 PiCANet [40] 0.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, background): “, 2017], PICANet [Liu et al., 2018a], Liu et al.”
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].”
Shifting More Attention to Video Salient Object Detection (2019, background): “More recently, deep learning based VSOD models [31, 38, 39, 41, 67, 68, 76] have gained more attention inspired by the success of applying deep neural networks on image saliency detection [13–15,32,50,71,72,86,88–90,94].”
Visual Saliency Transformer (2021, methodology): “Although some methods utilized fully connected layers [36, 22], global pooling layers [44, 37, 65], and non-local modules [38, 7] to incorporate the global context, they only did such in certain layers and the standard CNN-based architecture remains unchanged.”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, background): “8, which is widely adopted in (Hou et al. 2019; Liu, Han, and Yang 2018).”