Random Scaling
Description
Random Scaling is a type of image data augmentation in which we randomly change the scale of the image within a specified range.
The Albumentations library has generalization of the RandomScaling called Affine
Affine transform allows randomly scale as RandomScaling, but you may also randomly rotate, translate, and shear.
Papers Using This Method
Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling2025-05-23Asymptotic Analysis of Sample-averaged Q-learning2024-10-14Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique2024-09-03Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects2022-12-02Learning to Disentangle Scenes for Person Re-identification2021-11-10Statistical Estimation and Inference via Local SGD in Federated Learning2021-09-03MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection2020-01-09PointRend: Image Segmentation as Rendering2019-12-17Bottom-up Object Detection by Grouping Extreme and Center Points2019-01-23Panoptic Feature Pyramid Networks2019-01-08ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation2018-03-19Rethinking Atrous Convolution for Semantic Image Segmentation2017-06-17DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs2016-06-02