Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments

• URL: http://arxiv.org/abs/2205.11722v2
• Date: Mon, 22 May 2023 22:02:03 GMT
• Title: Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
• Authors: Rajhans Singh (1), Ankita Shukla (1), Pavan Turaga (1) ((1) Arizona State University)
• Abstract summary: Deep networks for image classification often rely more on texture information than object shape. This paper presents a deep-learning model inspired by geometric moments. We demonstrate the effectiveness of our method on standard image classification datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant yet in a task-specific manner. The proposed model improves the final feature's interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance compared to the baseline and standard ResNet models while substantially improving interpretability.

Related papers

• Segmenting objects with Bayesian fusion of active contour models and convnet priors [0.729597981661727]
  We propose a novel instance segmentation method geared towards Natural Resource Monitoring (NRM) imagery. We formulate the problem as Bayesian maximum a posteriori inference which, in learning the individual object contours, incorporates shape, location, and position priors. In experiments, we tackle the challenging, real-world problem of segmenting individual dead tree crowns and precise contours.
  arXiv  Detail & Related papers  (2024-10-09T20:36:43Z)
• Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers [8.781861951759948]
  This paper presents Geo-SIC, the first deep learning model to learn deformable shapes in a deformation space for an improved performance of image classification. We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations. We develop a boosted classification network, equipped with an unsupervised learning of geometric shape representations.
  arXiv  Detail & Related papers  (2022-10-25T01:55:17Z)
• Anisotropic Multi-Scale Graph Convolutional Network for Dense Shape Correspondence [3.45989531033125]
  This paper studies 3D dense shape correspondence, a key shape analysis application in computer vision and graphics. We introduce a novel hybrid geometric deep learning-based model that learns geometrically meaningful and discretization-independent features. The resulting correspondence maps show state-of-the-art performance on the benchmark datasets.
  arXiv  Detail & Related papers  (2022-10-17T22:40:50Z)
• Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction [62.691996239590125]
  We propose an adaptive convolutional dictionary network (ACDNet) for metal artifact reduction. Our ACDNet can automatically learn the prior for artifact-free CT images via training data and adaptively adjust the representation kernels for each input CT image. Our method inherits the clear interpretability of model-based methods and maintains the powerful representation ability of learning-based methods.
  arXiv  Detail & Related papers  (2022-05-16T06:49:36Z)
• Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport [80.64516377977183]
  Shape matching has been a long-studied problem for the computer graphics and vision community. We investigate a hierarchical learning design, to which we incorporate local patch-level information and global shape-level structures. We propose a novel optimal transport solver by recurrently updating features on non-confident nodes to learn globally consistent correspondences between the shapes.
  arXiv  Detail & Related papers  (2022-02-03T11:41:46Z)
• SurFit: Learning to Fit Surfaces Improves Few Shot Learning on Point Clouds [48.61222927399794]
  SurFit is a simple approach for label efficient learning of 3D shape segmentation networks. It is based on a self-supervised task of decomposing the surface of a 3D shape into geometric primitives.
  arXiv  Detail & Related papers  (2021-12-27T23:55:36Z)
• Representing Shape Collections with Alignment-Aware Linear Models [17.635846912560627]
  We revisit the classical representation of 3D point clouds as linear shape models. Our key insight is to leverage deep learning to represent a collection of shapes as affine transformations.
  arXiv  Detail & Related papers  (2021-09-03T16:28:34Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)
• Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation [62.618227434286]
  We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. We propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior.
  arXiv  Detail & Related papers  (2020-07-16T16:45:05Z)
• Neural Subdivision [58.97214948753937]
  This paper introduces Neural Subdivision, a novel framework for data-driven coarseto-fine geometry modeling. We optimize for the same set of network weights across all local mesh patches, thus providing an architecture that is not constrained to a specific input mesh, fixed genus, or category. We demonstrate that even when trained on a single high-resolution mesh our method generates reasonable subdivisions for novel shapes.
  arXiv  Detail & Related papers  (2020-05-04T20:03:21Z)

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.