One Point is All You Need: Directional Attention Point for Feature Learning

• URL: http://arxiv.org/abs/2012.06257v2
• Date: Mon, 14 Dec 2020 06:47:12 GMT
• Title: One Point is All You Need: Directional Attention Point for Feature Learning
• Authors: Liqiang Lin, Pengdi Huang, Chi-Wing Fu, Kai Xu, Hao Zhang, Hui Huang
• Abstract summary: We present a novel attention-based mechanism for learning enhanced point features for tasks such as point cloud classification and segmentation. We show that our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks.
• Score: 51.44837108615402
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a novel attention-based mechanism for learning enhanced point features for tasks such as point cloud classification and segmentation. Our key message is that if the right attention point is selected, then "one point is all you need" -- not a sequence as in a recurrent model and not a pre-selected set as in all prior works. Also, where the attention point is should be learned, from data and specific to the task at hand. Our mechanism is characterized by a new and simple convolution, which combines the feature at an input point with the feature at its associated attention point. We call such a point a directional attention point (DAP), since it is found by adding to the original point an offset vector that is learned by maximizing the task performance in training. We show that our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks. Extensive experiments on common benchmarks such as ModelNet40, ShapeNetPart, and S3DIS demonstrate that our DAP-enabled networks consistently outperform the respective original networks, as well as all other competitive alternatives, including those employing pre-selected sets of attention points.

Related papers

• DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning [23.048005152646592]
  We propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between point parts. We devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training. The proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks.
  arXiv  Detail & Related papers  (2024-01-05T02:54:23Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• ResMatch: Residual Attention Learning for Local Feature Matching [51.07496081296863]
  We rethink cross- and self-attention from the viewpoint of traditional feature matching and filtering. We inject the similarity of descriptors and relative positions into cross- and self-attention score. We mine intra- and inter-neighbors according to the similarity of descriptors and relative positions.
  arXiv  Detail & Related papers  (2023-07-11T11:32:12Z)
• D-Net: Learning for Distinctive Point Clouds by Self-Attentive Point Searching and Learnable Feature Fusion [48.57170130169045]
  We propose D-Net to learn for distinctive point clouds based on a self-attentive point searching and a learnable feature fusion. To generate a compact feature representation for each distinctive point set, a stacked self-gated convolution is proposed to extract the distinctive features. The results show that the learned distinction distribution of a point cloud is highly consistent with objects of the same class and different from objects of other classes.
  arXiv  Detail & Related papers  (2023-05-10T02:19:00Z)
• Towards Class-agnostic Tracking Using Feature Decorrelation in Point Clouds [9.321928362927965]
  Single object tracking in point clouds has been attracting more and more attention owing to the presence of LiDAR sensors in 3D vision. Existing methods based on deep neural networks focus mainly on training different models for different categories. In this work, we turn our thoughts to a more challenging task in the LiDAR point clouds, class-agnostic tracking.
  arXiv  Detail & Related papers  (2022-02-28T03:33:03Z)
• FatNet: A Feature-attentive Network for 3D Point Cloud Processing [1.502579291513768]
  We introduce a novel feature-attentive neural network layer, a FAT layer, that combines both global point-based features and local edge-based features in order to generate better embeddings. Our architecture achieves state-of-the-art results on the task of point cloud classification, as demonstrated on the ModelNet40 dataset.
  arXiv  Detail & Related papers  (2021-04-07T23:13:56Z)
• Coordinate Attention for Efficient Mobile Network Design [96.40415345942186]
  We propose a novel attention mechanism for mobile networks by embedding positional information into channel attention. Unlike channel attention that transforms a feature tensor to a single feature vector via 2D global pooling, the coordinate attention factorizes channel attention into two 1D feature encoding processes. Our coordinate attention is beneficial to ImageNet classification and behaves better in down-stream tasks, such as object detection and semantic segmentation.
  arXiv  Detail & Related papers  (2021-03-04T09:18:02Z)
• Deep Reinforced Attention Learning for Quality-Aware Visual Recognition [73.15276998621582]
  We build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks. We introduce a meta critic network to evaluate the quality of attention maps in the main network.
  arXiv  Detail & Related papers  (2020-07-13T02:44:38Z)
• SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints [7.223394571022494]
  This paper presents an end-to-end framework, SK-Net, to jointly optimize the inference of spatial keypoint with the learning of feature representation of a point cloud. Our proposed method performs better than or comparable with the state-of-the-art approaches in point cloud tasks.
  arXiv  Detail & Related papers  (2020-03-31T08:15:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.