mlsanityData to 14 Oct 2026

Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling

arXiv 2209.14431 ↗First posted 28 Sep 2022cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 28 Sep 2022.

Builds on

15 of 22 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  10. 2016Understanding data augmentation for classification: when to warp?cited by 74
  11. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 57
  12. 2022Resampling Images to a Regular Grid from a Non-Regular Subset of Pixel Positions Using Frequency Selective Reconstructioncited by 4
3 more
  1. 2022Real-Time Frequency Selective Reconstruction through Register-Based Argmax Calculationcited by 1
  2. 2022Key Point Agnostic Frequency-Selective Mesh-to-Grid Image Resampling using Spectral Weightingcited by 1
  3. 2022Motion-Adapted Three-Dimensional Frequency Selective Extrapolationcited by 1

Built on by

Not cited yet.