Neural Field Classifiers via Target Encoding and Classification Loss

• URL: http://arxiv.org/abs/2403.01058v1
• Date: Sat, 2 Mar 2024 01:20:59 GMT
• Title: Neural Field Classifiers via Target Encoding and Classification Loss
• Abstract summary: We propose a novel Neural Field (NFC) framework which formulates existing neural field methods as classification tasks. We demonstrate the impressive effectiveness of NFC at the nearly free extra computational costs.
• Score: 38.28073206783851
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural field methods have seen great progress in various long-standing tasks in computer vision and computer graphics, including novel view synthesis and geometry reconstruction. As existing neural field methods try to predict some coordinate-based continuous target values, such as RGB for Neural Radiance Field (NeRF), all of these methods are regression models and are optimized by some regression loss. However, are regression models really better than classification models for neural field methods? In this work, we try to visit this very fundamental but overlooked question for neural fields from a machine learning perspective. We successfully propose a novel Neural Field Classifier (NFC) framework which formulates existing neural field methods as classification tasks rather than regression tasks. The proposed NFC can easily transform arbitrary Neural Field Regressor (NFR) into its classification variant via employing a novel Target Encoding module and optimizing a classification loss. By encoding a continuous regression target into a high-dimensional discrete encoding, we naturally formulate a multi-label classification task. Extensive experiments demonstrate the impressive effectiveness of NFC at the nearly free extra computational costs. Moreover, NFC also shows robustness to sparse inputs, corrupted images, and dynamic scenes.

Related papers

• CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds [0.0]
  Existing spiking neural networks (SNNs) for class-incremental learning (CIL) suffer a sharp performance drop as tasks accumulate.<n>We here introduce CATFormer, a scalable framework that overcomes this limitation.<n>We observe that the key to preventing forgetting in SNNs lies not only in synaptic plasticity but also in modulating neuronal excitability.
  arXiv  Detail & Related papers  (2026-03-16T12:20:23Z)
• ViTNF: Leveraging Neural Fields to Boost Vision Transformers in Generalized Category Discovery [1.1970409518725493]
  Generalized category discovery (GCD) is a popular task in open-world recognition.<n>By leveraging pre-training, meta-training, and fine-tuning, ViT achieves excellent few-shot learning capabilities.<n>This paper proposes a new architecture by replacing the head with a neural field-based one.
  arXiv  Detail & Related papers  (2025-06-03T02:06:01Z)
• RelChaNet: Neural Network Feature Selection using Relative Change Scores [0.0]
  We introduce RelChaNet, a novel and lightweight feature selection algorithm that uses neuron pruning and regrowth in the input layer of a dense neural network. Our approach generally outperforms the current state-of-the-art methods, and in particular improves the average accuracy by 2% on the MNIST dataset.
  arXiv  Detail & Related papers  (2024-10-03T09:56:39Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Deep Learning for real-time neural decoding of grasp [0.0]
  We present a Deep Learning-based approach to the decoding of neural signals for grasp type classification. The main goal of the presented approach is to improve over state-of-the-art decoding accuracy without relying on any prior neuroscience knowledge.
  arXiv  Detail & Related papers  (2023-11-02T08:26:29Z)
• NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory [70.10550467873499]
  We propose NeuralClothSim, a new quasistatic cloth simulator using thin shells. Our memory-efficient solver operates on a new continuous coordinate-based surface representation called neural deformation fields.
  arXiv  Detail & Related papers  (2023-08-24T17:59:54Z)
• Progressive Fourier Neural Representation for Sequential Video Compilation [75.43041679717376]
  Motivated by continual learning, this work investigates how to accumulate and transfer neural implicit representations for multiple complex video data over sequential encoding sessions. We propose a novel method, Progressive Fourier Neural Representation (PFNR), that aims to find an adaptive and compact sub-module in Fourier space to encode videos in each training session. We validate our PFNR method on the UVG8/17 and DAVIS50 video sequence benchmarks and achieve impressive performance gains over strong continual learning baselines.
  arXiv  Detail & Related papers  (2023-06-20T06:02:19Z)
• Semantic-Based Neural Network Repair [4.092001692194709]
  We propose an approach to automatically repair erroneous neural networks. Our approach is based on an executable semantics of deep learning layers. We evaluate our approach for two usage scenarios, i.e., repairing automatically generated neural networks and manually written ones suffering from common model bugs.
  arXiv  Detail & Related papers  (2023-06-12T16:18:32Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Neural networks with linear threshold activations: structure and algorithms [1.795561427808824]
  We show that 2 hidden layers are necessary and sufficient to represent any function representable in the class. We also give precise bounds on the sizes of the neural networks required to represent any function in the class. We propose a new class of neural networks that we call shortcut linear threshold networks.
  arXiv  Detail & Related papers  (2021-11-15T22:33:52Z)
• A Sparse Coding Interpretation of Neural Networks and Theoretical Implications [0.0]
  Deep convolutional neural networks have achieved unprecedented performance in various computer vision tasks. We propose a sparse coding interpretation of neural networks that have ReLU activation. We derive a complete convolutional neural network without normalization and pooling.
  arXiv  Detail & Related papers  (2021-08-14T21:54:47Z)
• Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
  We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
  arXiv  Detail & Related papers  (2020-02-02T21:09:39Z)

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.