ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning

By Weiwei Sun, Wei Jiang, Eduard Trulls, Andrea Tagliasacchi, Kwang Moo Yi. 2020

158 citations recorded by the source corpus.

Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds. Permutation-equivariant networks have become a popular solution – they operate on individual data points with simple perceptrons and extract contextual information with global pooling. This can be achieved with a simple normalization of the feature maps, a global operation that is unaffected by the order. In this paper, we propose Attentive Context Normalization (ACN), a simple yet effective technique to build permutation-equivariant networks robust to outliers. Specifically, we show how to normalize the feature maps with weights that are estimated within the network, excluding outliers from this normalization. We use this mechanism to leverage two types of attention: local and global – by combining them, our method is able to find the essential data points in high-dimensional space in order to solve a given task. We demonstrate through extensive experiments that our approach, which we call Attentive Context Networks (ACNe), provides a significant leap in performance compared to the state-of-the-art on camera pose estimation, robust fitting, and point cloud classification under noise and outliers. Source code: https://github.com/vcg-uvic/acne.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

How to Represent Part-Whole Hierarchies in a Neural Network (2021, methodology): “The way attention is intended to work in GLOM has already been used successfully in a system called ”ACNe” [Sun et al., 2020a].”
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency (2021, methodology): “Learning-based outlier rejection methods are first introduced in the 2D image matching task [46, 73, 74, 60], where outlier rejection is formulated as an inlier/outlier classification problem.”
Image Matching Across Wide Baselines: From Paper to Practice (2020, methodology): “2017), sparking a number of follow-up works (Ranftl and Koltun 2018; Dang et al. 2018; Zhao et al. 2019; Zhang et al. 2019; Sun et al. 2020).”
COTR: Correspondence Transformer for Matching Across Images (2021, background): “They rely on local features [34, 74, 44, 13] and further prune the putative correspondences formed with them in a separate stage with sampling-based robust matchers [18, 3, 12], or their learned counterparts [75, 7, 76, 64, 54].”
Normalization Techniques in Training DNNs: Methodology, Analysis and Application (2020, background): “However, we note that there also exist works exploring how to apply normalization to meta learning [59], [214], [215], reinforcement learning [216], [217], [218], unsupervised representation learning [219], [220], permutation-equivariant networks [221], [222], graph neural networks [223], ordinary d”
Towards Deeper Graph Neural Networks with Differentiable Group Normalization (2020, methodology): “Parallel to this research, the similar group normalization approaches of attentive normalization (AN) [32] and attentive context normalization (ACN) [33] are used for the semantic segmentation at computer vision domain.”