End-to-End Implicit Neural Representations for Classification

• URL: http://arxiv.org/abs/2503.18123v1
• Date: Sun, 23 Mar 2025 16:02:23 GMT
• Title: End-to-End Implicit Neural Representations for Classification
• Authors: Alexander Gielisse, Jan van Gemert,
• Abstract summary: Implicit neural representations (INRs) encode a signal in neural network parameters and show excellent results for signal reconstruction.<n>INR-based classification still significantly under-performs compared to pixel-based methods like CNNs.<n>This work presents an end-to-end strategy for initializing SIRENs together with a learned learning-rate scheme.
• Score: 57.55927378696826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Implicit neural representations (INRs) such as NeRF and SIREN encode a signal in neural network parameters and show excellent results for signal reconstruction. Using INRs for downstream tasks, such as classification, is however not straightforward. Inherent symmetries in the parameters pose challenges and current works primarily focus on designing architectures that are equivariant to these symmetries. However, INR-based classification still significantly under-performs compared to pixel-based methods like CNNs. This work presents an end-to-end strategy for initializing SIRENs together with a learned learning-rate scheme, to yield representations that improve classification accuracy. We show that a simple, straightforward, Transformer model applied to a meta-learned SIREN, without incorporating explicit symmetry equivariances, outperforms the current state-of-the-art. On the CIFAR-10 SIREN classification task, we improve the state-of-the-art without augmentations from 38.8% to 59.6%, and from 63.4% to 64.7% with augmentations. We demonstrate scalability on the high-resolution Imagenette dataset achieving reasonable reconstruction quality with a classification accuracy of 60.8% and are the first to do INR classification on the full ImageNet-1K dataset where we achieve a SIREN classification performance of 23.6%. To the best of our knowledge, no other SIREN classification approach has managed to set a classification baseline for any high-resolution image dataset. Our code is available at https://github.com/SanderGielisse/MWT

Related papers

• Neural Edge Histogram Descriptors for Underwater Acoustic Target Recognition [42.23422932643755]
  This work adapts the neural edge histogram descriptors (NEHD) method originally developed for image classification, to classify passive sonar signals.<n>We conduct a comprehensive evaluation of statistical and structural texture features, demonstrating that their combination achieves competitive performance with large pre-trained models.<n>The proposed NEHD-based approach offers a lightweight and efficient solution for underwater target recognition, significantly reducing computational costs while maintaining accuracy.
  arXiv  Detail & Related papers  (2025-03-17T22:57:05Z)
• Meta-INR: Efficient Encoding of Volumetric Data via Meta-Learning Implicit Neural Representation [4.782024723712711]
  Implicit neural representation (INR) has emerged as a promising solution for encoding volumetric data.<n>We propose Meta-INR, a pretraining strategy adapted from meta-learning algorithms to learn initial INR parameters from partial observation of a dataset.<n>We demonstrate that Meta-INR can effectively extract high-quality generalizable features that help encode unseen similar volume data across diverse datasets.
  arXiv  Detail & Related papers  (2025-02-12T21:54:22Z)
• NMformer: A Transformer for Noisy Modulation Classification in Wireless Communication [19.225546116534165]
  We propose a vision transformer (ViT) based model named NMformer to predict the channel modulation images with different noise levels in wireless communication. Since ViTs are most effective for RGB images, we generated constellation diagrams from the modulated signals. Our proposed model has two different kinds of prediction setups: in-distribution and out-of-distribution.
  arXiv  Detail & Related papers  (2024-10-30T21:10:12Z)
• IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition [13.783950035836593]
  IncSAR is an incremental learning framework designed to tackle catastrophic forgetting in target recognition.<n>To mitigate the speckle noise inherent in SAR images, we employ a denoising module based on a neural network approximation.<n>Experiments on the MSTAR, SAR-AIRcraft-1.0, and OpenSARShip benchmark datasets demonstrate that IncSAR significantly outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-08T08:49:47Z)
• Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity [55.399230250413986]
  We propose a Quality-Aware Feature Matching IQA Metric (QFM-IQM) to remove harmful semantic noise features from the upstream task. Our approach achieves superior performance to the state-of-the-art NR-IQA methods on eight standard IQA datasets.
  arXiv  Detail & Related papers  (2023-12-11T06:50:27Z)
• Prompt Tuning for Parameter-efficient Medical Image Segmentation [79.09285179181225]
  We propose and investigate several contributions to achieve a parameter-efficient but effective adaptation for semantic segmentation on two medical imaging datasets. We pre-train this architecture with a dedicated dense self-supervision scheme based on assignments to online generated prototypes. We demonstrate that the resulting neural network model is able to attenuate the gap between fully fine-tuned and parameter-efficiently adapted models.
  arXiv  Detail & Related papers  (2022-11-16T21:55:05Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers [16.244541005112747]
  Convolutional Neural Networks (CNNs) are one of the most studied family of deep learning models for signal classification. We focus on technology classification based on raw I/Q samples collected from multiple synchronized receivers.
  arXiv  Detail & Related papers  (2022-04-28T23:41:38Z)
• From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks [82.21746840893658]
  This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. We show that while the ResNet-18 model trained on DWT spectrograms achieves a high recognition accuracy, attacking this model is relatively more costly for the adversary.
  arXiv  Detail & Related papers  (2022-04-14T15:14:08Z)
• Sequence Transduction with Graph-based Supervision [96.04967815520193]
  We present a new transducer objective function that generalizes the RNN-T loss to accept a graph representation of the labels. We demonstrate that transducer-based ASR with CTC-like lattice achieves better results compared to standard RNN-T.
  arXiv  Detail & Related papers  (2021-11-01T21:51:42Z)
• Deep Networks for Direction-of-Arrival Estimation in Low SNR [89.45026632977456]
  We introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true array manifold matrix. We train a CNN in the low-SNR regime to predict DoAs across all SNRs. Our robust solution can be applied in several fields, ranging from wireless array sensors to acoustic microphones or sonars.
  arXiv  Detail & Related papers  (2020-11-17T12:52:18Z)

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.