There are 3 repositories under multi-scale topic.
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).
[TVCG'2023] AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)
An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).
PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models
[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation
[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation in CVPR 2017 (Spotlight)
Open Scripts and pipelines from the Multimodal Imaging and Connectome Analysis Lab at the Montreal Neurological Institute
The implementation of FDCNN in paper - A Feature Difference Convolutional Neural Network-Based Change Detection Method
Fully supervised binary classification of skin lesions from dermatoscopic images using an ensemble of diverse CNN architectures (EfficientNet-B6, Inception-V3, SEResNeXt-101, SENet-154, DenseNet-169) with multi-scale input.
An PyTorch implementation of Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
PyTorch implementation of "Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration"
Implementation of "SpEx: Multi-Scale Time Domain Speaker Extraction Network".
Res2Net for Panoptic Segmentation based on detectron2 (SOTA results).
Core Interface and Engine for Vivarium 1.0
Accompaniment code for 'Hilbert sEMG data scanning for hand gesture recognition based on Deep Learning' published in NCAA.
Multi-scale deep neural networks for real image super-resolution
The MultiScale Network for hierarchical regression (MS-Net) performs 3D regression based on a hierarchical principle: coarse inputs provide broad information about the data, and progressively finer-scale inputs can be used to refine this information.
Semantic Labeling in VHR Images via A Self-Cascaded CNN (ISPRS JPRS, IF=6.942)
A parallel multi-scale FE2 code based on COMSOL Multi-physics and MATLAB
Pytorch Implementation of Residual Multiplicative Filter Networks, NeurIPS 2022
Multi-scale network for image deblurring
This is an example to find multiple objects in images that match a template using ORB and SIFT feature detection methods. Handles different scales and rotations.
PyTorch implementation of "Reconstruction by inpainting for visual anomaly detection (RIAD)"
Dynamic Multi-Context Segmentation of Remote Sensing Images based on Convolutional Networks
U-Net + Attention, extending U-Net model for semantic segmentation. Implemented with TensorFlow.
Codes and data for a published work "Multi-scale detection and interpretation of spatio-temporal anomalies of human activities represented by time-series"
A distributed implementation of "Nested Subtree Hash Kernels for Large-Scale Graph Classification Over Streams" (ICDM 2012).
Webpage: https://jgcri.github.io/metis/ Cheatsheet: https://github.com/JGCRI/metis/blob/master/metisCheatsheet.pdf
Multi-scale 4D-Earth framework front-end
MPI-based code for distributed HPC simulations with the sparse grid combination technique. Docs->(https://discotec.readthedocs.io/)