Rigid-Motion Scattering for Texture Classification

Abstract

A rigid-motion scattering computes adaptive invariants along translations and rotations, with a deep convolutional network. Convolutions are calculated on the rigid-motion group, with wavelets defined on the translation and rotation variables. It preserves joint rotation and translation information, while providing global invariants at any desired scale. Texture classification is studied, through the characterization of stationary processes from a single realization. State-of-the-art results are obtained on multiple texture data bases, with important rotation and scaling variabilities.

19 pages, submitted to International Journal of Computer Vision

Cited by in corpus (28)

• Twins: Revisiting the Design of Spatial Attention in Vision Transformers
• Aggregated Residual Transformations for Deep Neural Networks
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• IL-MCAM: An interactive learning and multi-channel attention mechanism-based weakly supervised colorectal histopathology image classification approach
• Co-training for Demographic Classification Using Deep Learning from Label Proportions
• Large Kernel Distillation Network for Efficient Single Image Super-Resolution
• PDE-based Group Equivariant Convolutional Neural Networks
• s-LWSR: Super Lightweight Super-Resolution Network
• Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
• QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
• Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture
• Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
• File Fragment Classification using Light-Weight Convolutional Neural Networks
• Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
• Geometric Scattering for Graph Data Analysis
• Geometric Scattering on Manifolds
• Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds
• CUNet: A Compact Unsupervised Network for Image Classification
• Parameter Prediction for Unseen Deep Architectures
• IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
• Prune2Edge: A Multi-Phase Pruning Pipelines to Deep Ensemble Learning in IIoT
• Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset
• On the signature of an image
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• Audio Spectral Enhancement: Leveraging Autoencoders for Low Latency Reconstruction of Long, Lossy Audio Sequences
• Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
• IC-Network: Efficient Structure for Convolutional Neural Networks
• A CNN Accelerator on FPGA Using Depthwise Separable Convolution