paper-with-me

Papers

Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations

2023-03-14 · CVPR 2023 1 · Hagay Michaeli, Tomer Michaeli, Daniel Soudry

Although CNNs are believed to be invariant to translations, recent works have shown this is not the case, due to aliasing effects that stem from downsampling layers. The existing architectural solutions to prevent aliasing are partial since they do not solve these effects, that originate in non-linearities. We propose an extended anti-aliasing method that tackles both downsampling and non-linear layers, thus creating truly alias-free, shift-invariant CNNs. We show that the presented model is invariant to integer as well as fractional (i.e., sub-pixel) translations, thus outperforming other shift-invariant methods in terms of robustness to adversarial translations.

📄 PDF Abstract BibTeX arXiv:2303.08085

Code (1)

hmichaeli/alias_free_convnets 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

2025-10-26 · Hagay Michaeli, Daniel Soudry arxiv

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transform…

Image Classification

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space

2025-01-01 · CVPR 2025 1 · Yifan Zhou, Zeqi Xiao, Shuai Yang, Xingang Pan

Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different outputs. This hinders their applicabili…

Image-to-Image TranslationVideo Editing

Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space

2025-03-12 · Yifan Zhou, Zeqi Xiao, Shuai Yang, Xingang Pan

Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different outputs. This hinders their applicability i…

Image-to-Image TranslationVideo Editing

What Does CNN Shift Invariance Look Like? A Visualization Study

2020-11-09 · Jake Lee, Junfeng Yang, Zhangyang Wang

Feature extraction with convolutional neural networks (CNNs) is a popular method to represent images for machine learning tasks. These representations seek to capture global image content, and ideally should be independe…

How ConvNets model Non-linear Transformations

2017-02-24 · Dipan K. Pal, Marios Savvides

In this paper, we theoretically address three fundamental problems involving deep convolutional networks regarding invariance, depth and hierarchy. We introduce the paradigm of Transformation Networks (TN) which are a di…

model