Deep Parametric Continuous Convolutional Neural Networks

• URL: http://arxiv.org/abs/2101.06742v1
• Date: Sun, 17 Jan 2021 18:28:23 GMT
• Title: Deep Parametric Continuous Convolutional Neural Networks
• Authors: Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei Pokrovsky, Raquel Urtasun
• Abstract summary: Parametric Continuous Convolution is a new learnable operator that operates over non-grid structured data. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes.
• Score: 92.87547731907176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

Related papers

• A Resolution Independent Neural Operator [0.0]
  We introduce RINO, which provides a framework to make DeepONet resolution-independent. RINO allows DeepONet to handle input functions that are arbitrarily, but sufficiently finely, discretized. We demonstrate the robustness and applicability of RINO in handling arbitrarily (but sufficiently richly) sampled input and output functions.
  arXiv  Detail & Related papers  (2024-07-17T21:03:21Z)
• Do deep neural networks have an inbuilt Occam's razor? [1.1470070927586016]
  We show that structured data combined with an intrinsic Occam's razor-like inductive bias towards simple functions counteracts the exponential growth of functions with complexity. This analysis reveals that structured data, combined with an intrinsic Occam's razor-like inductive bias towards (Kolmogorov) simple functions that is strong enough to counteract the exponential growth of functions with complexity, is a key to the success of DNNs.
  arXiv  Detail & Related papers  (2023-04-13T16:58:21Z)
• PDSketch: Integrated Planning Domain Programming and Learning [86.07442931141637]
  We present a new domain definition language, named PDSketch. It allows users to flexibly define high-level structures in the transition models. Details of the transition model will be filled in by trainable neural networks.
  arXiv  Detail & Related papers  (2023-03-09T18:54:12Z)
• Neural Attentive Circuits [93.95502541529115]
  We introduce a general purpose, yet modular neural architecture called Neural Attentive Circuits (NACs) NACs learn the parameterization and a sparse connectivity of neural modules without using domain knowledge. NACs achieve an 8x speedup at inference time while losing less than 3% performance.
  arXiv  Detail & Related papers  (2022-10-14T18:00:07Z)
• Graph Kernel Neural Networks [53.91024360329517]
  We propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability.
  arXiv  Detail & Related papers  (2021-12-14T14:48:08Z)
• DeltaConv: Anisotropic Point Cloud Learning with Exterior Calculus [13.18401177210079]
  We introduce a new convolution operator called DeltaConv, which combines geometric operators from exterior calculus to enable the construction of anisotropic filters on point clouds. Our convolutions are robust and simple to implement and show improved accuracy compared to state-of-the-art approaches on several benchmarks.
  arXiv  Detail & Related papers  (2021-11-16T21:58:55Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Compressing Deep ODE-Nets using Basis Function Expansions [105.05435207079759]
  We consider formulations of the weights as continuous-depth functions using linear combinations of basis functions. This perspective allows us to compress the weights through a change of basis, without retraining, while maintaining near state-of-the-art performance. In turn, both inference time and the memory footprint are reduced, enabling quick and rigorous adaptation between computational environments.
  arXiv  Detail & Related papers  (2021-06-21T03:04:51Z)
• Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks [29.3830445533532]
  Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Applying deep learning techniques to perform point cloud analysis is non-trivial due to the inability of these methods to generalize to unseen rotations. To address this limitation, one usually has to augment the training data, which can lead to extra computation and require larger model complexity. This paper proposes a new neural network called the Aligned Edge Convolutional Neural Network (AECNN) that learns a feature representation of point clouds relative to Local Reference Frames (LRFs)
  arXiv  Detail & Related papers  (2021-01-02T17:36:00Z)

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.