AI Chat AI Image Generator AI Video Text to Speech

Patch DCT vs LeNet

11/04/2022

∙

by David Sinclair, et al.

∙

∙

This paper compares the performance of a NN taking the output of a DCT (Discrete Cosine Transform) of an image patch with leNet for classifying MNIST hand written digits. The basis functions underlying the DCT bear a passing resemblance to some of the learned basis function of the Visual Transformer but are an order of magnitude faster to apply.

page 3

page 4

page 5

research

∙ 09/01/2023

Adaptive function approximation based on the Discrete Cosine Transform (DCT)

This paper studies the cosine as basis function for the approximation of...

0 Ana I. Perez-Neira, et al. ∙

research

∙ 04/28/2020

Minority Reports Defense: Defending Against Adversarial Patches

Deep learning image classification is vulnerable to adversarial attack, ...

8 Michael McCoyd, et al. ∙

research

∙ 01/02/2021

C^1 isogeometric spline space for trilinearly parameterized multi-patch volumes

We study the space of C^1 isogeometric spline functions defined on trili...

0 Mario Kapl, et al. ∙

research

∙ 06/15/2023

ANOVA approximation with mixed tensor product basis on scattered points

In this paper we consider an orthonormal basis, generated by a tensor pr...

0 Daniel Potts, et al. ∙

research

∙ 12/12/2018

Thwarting Adversarial Examples: An L_0-RobustSparse Fourier Transform

We give a new algorithm for approximating the Discrete Fourier transform...

10 Mitali Bafna, et al. ∙

research

∙ 03/22/2022

Learning Patch-to-Cluster Attention in Vision Transformer

The Vision Transformer (ViT) model is built on the assumption of treatin...

1 Ryan Grainger, et al. ∙

research

∙ 05/16/2023

Ray-Patch: An Efficient Decoder for Light Field Transformers

In this paper we propose the Ray-Patch decoder, a novel model to efficie...

0 T. B. Martins, et al. ∙