Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
-
Updated
Jun 18, 2025 - Python
Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
Code for ICLR2021 paper "Robust and Generalizable Visual Representation Learning via Random Convolutions"
Official code release for the paper Trapped in texture bias? A large scale comparison of deep instance segmentation, accepted at ECCV 2022
A study on the effect of normalization in predictions by CNN models
"On the Prevalence of Texture Bias in Deep Learning Models for Remote Sensing" - Systematically exploring feature bias in a wide range of CNN and Transformer architectures
In this work we explore whether MLPs are naturally biased towards using shape or texture as the main feature for image classification decisions.
Add a description, image, and links to the texture-bias topic page so that developers can more easily learn about it.
To associate your repository with the texture-bias topic, visit your repo's landing page and select "manage topics."