PSANet: Point-wise Spatial Attention Network for Scene Parsing

By Hengshuang Zhao, Yi Zhang, Shu Liu, Jianping Shi, Chen Change Loy, Dahua Lin, Jiaya Jia. 2018

1,127 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Exploring Self-Attention for Image Recognition (2020, neutral): “This has inspired applications of self-attention and related ideas to image recognition [5, 34, 15, 14, 45, 46, 13, 1, 27], image synthesis [43, 26, 2], image captioning [39, 41, 4], and video prediction [17, 35].”
CCNet: Criss-Cross Attention for Semantic Segmentation (2018, methodology): “Most of methods [5, 22, 40, 27, 30, 41, 35, 19, 42, 36] adopt the same backbone as ours and the others [32, 34] utilize stronger backbones.”
VOLO: Vision Outlooker for Visual Recognition (2021, neutral): “vision task [22], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
Panoptic Feature Pyramid Networks (2019, methodology): “ntic segmentation: FCNs [41] serve as the foundation of modern semantic segmentation methods. To increase feature resolution, which is necessary for generating highquality results, recent top methods [12,58,5,59] rely heavily on the use of dilated convolution [57] (also known as atrous convolution [”
K-Net: Towards Unified Image Segmentation (2021, background): “Based on this framework, many studies focus on enhancing the feature representation through dilated convolution [7–9], pyramid pooling [59, 69], context representations [66, 67], and attention mechanisms [32, 65, 70].”
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers (2020, background): “Both classes of methods have boosted various vision tasks such as image classification [18, 5, 72, 37, 57, 89, 28], object detection [91, 80, 72, 36, 10, 108], semantic segmentation [15, 106, 39, 29, 109, 107], video recognition [91, 18], image generation [73, 35], and panoptic segmentation [89].”
PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “Examples of recent works exploiting contextual information include attention mechanisms [69, 76, 22, 30, 68, 61, 73], and fixed-scale aggregation [75, 12, 11, 72].”
Dual Attention Network for Scene Segmentation (2018, methodology): “In particular, our model outperforms PSANet [30] by a large margin with the same backbone ResNet-101.”
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers (2020, background): “PSANet [59] develops the pointwise spatial attention module for dynamically capturing the long range context.”
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (2021, methodology): “Self-attention in CNN Self-attention mechanism has been widely applied to CNN in vision task [38, 55, 19, 47, 20, 39, 1, 6, 18, 31, 42, 13].”
Deep High-Resolution Representation Learning for Visual Recognition (2019, methodology): “The Cityscapes dataset [28] contains 5 , 000 high We follow the same training protocol [181], [182].”
Segmenter: Transformer for Semantic Segmentation (2021, methodology): “Following recent progresses in NLP [47], several segmentation methods explore alternative aggregation schemes based on channel or spatial [20, 21, 57] attention and point-wise [61] attention to better capture contextual information.”
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (2021, neutral): “[43] ResNet-101 IM-1K 80.1 CCNet [41] ResNet-101 IM-1K 81.9 OCNet [21] ResNet-101 IM-1K 80.1 Axial-DeepLab [74] AxiaiResNet-XL IM-1K 79.9 SETR [7] ViT IM-22K 81.0 SETR [7] ViT IM-22K, Coarse 81.”
An Empirical Study of Spatial Attention Mechanisms in Deep Networks (2019, methodology): “The success of attention modeling in NLP has led to its adoption in computer vision, where different variants of Transformer attention are applied to recognition tasks such as object detection and semantic segmentation [20, 38, 17, 22, 46, 13], where the query and key are visual elements such as ima”
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing (2020, background): “One way to improve the capability of modeling the long-range dependencies in CNNs is to adopt self-attention or non-local modules [51, 23, 7, 45, 21, 53, 66, 62, 61, 28].”
OCNet: Object Context Network for Scene Parsing (2018, background): “The PSANet constructs the pixel-wise attention map based on each pixel independently while OCNet constructs the object context map by considering the pair-wise similarities among all the pixels.”
Image Segmentation Using Deep Learning: A Survey (2020, background): “rent attention [97], a point-wise spatial attention network for scene parsing [98], and Discriminative Feature Network (DFN) [99].”