paper-with-me

홈 › Papers

Spatial Functa: Scaling Functa to ImageNet Classification and Generation

2023-02-06 · Matthias Bauer, Emilien Dupont, Andy Brock, Dan Rosenbaum, Jonathan Richard Schwarz, Hyunjik Kim

Neural fields, also known as implicit neural representations, have emerged as a powerful means to represent complex signals of various modalities. Based on this Dupont et al. (2022) introduce a framework that views neural fields as data, termed *functa*, and proposes to do deep learning directly on this dataset of neural fields. In this work, we show that the proposed framework faces limitations when scaling up to even moderately complex datasets such as CIFAR-10. We then propose *spatial functa*, which overcome these limitations by using spatially arranged latent representations of neural fields, thereby allowing us to scale up the approach to ImageNet-1k at 256x256 resolution. We demonstrate competitive performance to Vision Transformers (Steiner et al., 2022) on classification and Latent Diffusion (Rombach et al., 2022) on image generation respectively.

📄 PDF Abstract BibTeX arXiv:2302.03130

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

From data to functa: Your data point is a function and you can treat it like one

2022-01-28 · Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami, Danilo Rezende 외

It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often continuous, e.g. the …

Deep LearningImputationNeRFNovel View Synthesis

VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos

2025-07-29 · Julia Wolleb, Florentin Bieder, Paul Friedrich, Hemant D. Tagare 외 arxiv

Ultrasound is widely used in clinical care, yet standard deep learning methods often struggle with full video analysis due to non-standardized acquisition and operator bias. We offer a new perspective on ultrasound video…

Video ReconstructionLine Detection

Low-Rank-Modulated Functa: Exploring the Latent Space of Implicit Neural Representations for Interpretable Ultrasound Video Analysis

2026-03-26 · Julia Wolleb, Cristiana Baloescu, Alicia Durrer, Hemant D. Tagare 외 arxiv

Implicit neural representations (INRs) have emerged as a powerful framework for continuous image representation learning. In Functa-based approaches, each image is encoded as a latent modulation vector that conditions a …

Representation Learning

MedFuncta: Modality-Agnostic Representations Based on Efficient Neural Fields

2025-02-20 · Paul Friedrich, Florentin Bieder, Philippe C. Cattin

Recent research in medical image analysis with deep learning almost exclusively focuses on grid- or voxel-based data representations. We challenge this common choice by introducing MedFuncta, a modality-agnostic continuo…

Medical Image AnalysisMeta-Learning

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

2025-06-15 · Minju Jo, Woojin Cho, Uvini Balasuriya Mudiyanselage, Seungjun Lee 외

Scientific machine learning often involves representing complex solution fields that exhibit high-frequency features such as sharp transitions, fine-scale oscillations, and localized structures. While implicit neural rep…

Meta-Learning