paper-with-me

Papers

On Regularizing Coordinate-MLPs

2022-02-01 · Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey

We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in computer vision for representing high-frequency signals. Lack of such implicit bias disrupts smooth interpolations between training samples, and hampers generalizing across signal regions with different spectra. We investigate this behavior through a Fourier lens and uncover that as the bandwidth of a coordinate-MLP is enhanced, lower frequencies tend to get suppressed unless a suitable prior is provided explicitly. Based on these insights, we propose a simple regularization technique that can mitigate the above problem, which can be incorporated into existing networks without any architectural modifications.

📄 PDF Abstract BibTeX arXiv:2202.00790

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs

2021-11-30 · Sameera Ramasinghe, Simon Lucey

Coordinate-MLPs are emerging as an effective tool for modeling multidimensional continuous signals, overcoming many drawbacks associated with discrete grid-based approximations. However, coordinate-MLPs with ReLU activat…

MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision

2023-04-08 · Zhimin Zhu, Jianguo Zhao, Tong Mu, Yuliang Yang 외

In deep learning, Multi-Layer Perceptrons (MLPs) have once again garnered attention from researchers. This paper introduces MC-MLP, a general MLP-like backbone for computer vision that is composed of a series of fully-co…

Allimage-classificationImage Classification

Learning Positional Embeddings for Coordinate-MLPs

2021-12-21 · Sameera Ramasinghe, Simon Lucey

We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings. End-to-end optimization of positional embedding parameters along with network weights leads to …

Memorization

Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

2021-06-03 · Peng-Shuai Wang, Yang Liu, Yu-Qi Yang, Xin Tong

Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values. In this paper, we prop…

3D Shape ReconstructionImage Reconstruction

Well-tuned Simple Nets Excel on Tabular Datasets

2021-06-21 · NeurIPS 2021 12 · Arlind Kadra, Marius Lindauer, Frank Hutter, Josif Grabocka

Tabular datasets are the last "unconquered castle" for deep learning, with traditional ML methods like Gradient-Boosted Decision Trees still performing strongly even against recent specialized neural architectures. In th…