Scale-invariant Gaussian derivative residual networks
cs.CV, cs.LG
Submitted: 2026-03-03
Updated: 2026-09-25
Comments: 58 pages, 29 figures, 5 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
- The Master Key Filters Hypothesis: Deep Filters Are General
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
- Scale Steerable Filters for Locally Scale-Invariant Convolutional Neural Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Locally Scale-Invariant Convolutional Neural Networks
- Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
- Learning (Approximately) Equivariant Networks via Constrained Optimization
- Scale equivariance in CNNs with vector fields
- Ensembles provably learn equivariance through data augmentation
- DISCO: accurate Discrete Scale Convolutions
- EfficientNetV2: Smaller Models and Faster Training
- Scale-Equivariant Deep Learning for 3D Data
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Scale-Invariant Convolutional Neural Networks
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models