Meta-Continual Learning of Neural Fields

• URL: http://arxiv.org/abs/2504.05806v1
• Date: Tue, 08 Apr 2025 08:38:37 GMT
• Title: Meta-Continual Learning of Neural Fields
• Authors: Seungyoon Woo, Junhyeog Yun, Gunhee Kim,
• Abstract summary: This work unveils a new problem setting termed emphMeta-Continual Learning of Neural Fields (MCL-NF)<n>We introduce a novel strategy that employs a modular architecture combined with optimization-based meta-learning.<n>We perform evaluations across image, audio, video reconstruction, and view synthesis tasks on six diverse datasets.
• Score: 36.12465376767014
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural Fields (NF) have gained prominence as a versatile framework for complex data representation. This work unveils a new problem setting termed \emph{Meta-Continual Learning of Neural Fields} (MCL-NF) and introduces a novel strategy that employs a modular architecture combined with optimization-based meta-learning. Focused on overcoming the limitations of existing methods for continual learning of neural fields, such as catastrophic forgetting and slow convergence, our strategy achieves high-quality reconstruction with significantly improved learning speed. We further introduce Fisher Information Maximization loss for neural radiance fields (FIM-NeRF), which maximizes information gains at the sample level to enhance learning generalization, with proved convergence guarantee and generalization bound. We perform extensive evaluations across image, audio, video reconstruction, and view synthesis tasks on six diverse datasets, demonstrating our method's superiority in reconstruction quality and speed over existing MCL and CL-NF approaches. Notably, our approach attains rapid adaptation of neural fields for city-scale NeRF rendering with reduced parameter requirement.

Related papers

• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships. Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Learning Large-scale Neural Fields via Context Pruned Meta-Learning [60.93679437452872]
  We introduce an efficient optimization-based meta-learning technique for large-scale neural field training. We show how gradient re-scaling at meta-test time allows the learning of extremely high-quality neural fields. Our framework is model-agnostic, intuitive, straightforward to implement, and shows significant reconstruction improvements for a wide range of signals.
  arXiv  Detail & Related papers  (2023-02-01T17:32:16Z)
• MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation [3.0821115746307672]
  High-quality reconstruction of MRI images from under-sampled kspace' data is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. This paper introduces MA-RECON', an innovative mask-aware deep neural network (DNN) architecture and associated training method. It implements a tailored training approach that leverages data generated with a variety of under-sampling masks to stimulate the model's generalization of the under-sampled MRI reconstruction problem.
  arXiv  Detail & Related papers  (2022-08-31T15:57:38Z)
• GradMax: Growing Neural Networks using Gradient Information [22.986063120002353]
  We present a method that adds new neurons during training without impacting what is already learned, while improving the training dynamics. We call this technique Gradient Maximizing Growth (GradMax) and demonstrate its effectiveness in variety of vision tasks and architectures.
  arXiv  Detail & Related papers  (2022-01-13T18:30:18Z)
• SIRe-Networks: Skip Connections over Interlaced Multi-Task Learning and Residual Connections for Structure Preserving Object Classification [28.02302915971059]
  In this paper, we introduce an interlaced multi-task learning strategy, defined SIRe, to reduce the vanishing gradient in relation to the object classification task. The presented methodology directly improves a convolutional neural network (CNN) by enforcing the input image structure preservation through auto-encoders. To validate the presented methodology, a simple CNN and various implementations of famous networks are extended via the SIRe strategy and extensively tested on the CIFAR100 dataset.
  arXiv  Detail & Related papers  (2021-10-06T13:54:49Z)
• Influence Estimation and Maximization via Neural Mean-Field Dynamics [60.91291234832546]
  We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems. Our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.
  arXiv  Detail & Related papers  (2021-06-03T00:02:05Z)
• Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning [4.2903672492917755]
  We develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuromodulation. We demonstrate the efficacy of our approach on both single task and continual learning setting.
  arXiv  Detail & Related papers  (2020-07-16T07:41:23Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• An Ode to an ODE [78.97367880223254]
  We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the group O(d) This nested system of two flows provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem.
  arXiv  Detail & Related papers  (2020-06-19T22:05:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.