EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WaveConvNeXt: Wavelet-Guided Multi-Scale Feature Extraction with Frequency-Domain Attention for High-Fidelity Image Classification and Reconstruction

Saif Mohammed Ali

Journal of Computer Science Innovations and Research · 03.07.2026 · 2 (1) · 21-31

DOI: 10.69055/jcsir.v2i1.8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computer Science Innovations and Research, online erschienen am 03.07.2026. Verfasst von Saif Mohammed Ali. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep convolutional neural networks and Vision Transformers have achieved remarkable accuracy on large-scale image classification benchmarks, yet they predominantly operate in the spatial domain and fail to exploit the rich frequency-domain structure of natural images. Frequency information — encoded by wavelets as localized time-frequency representations — captures multi-resolution edge, texture, and periodic patterns that are complementary to the spatial receptive fields of convolutions and the global attention of Transformers. In this paper, we propose WaveConvNeXt, a hybrid deep learning architecture that integrates discrete wavelet transform (DWT) decompositions directly into the feature extraction pipeline of ConvNeXt-V2, augmented by a Frequency-Domain Attention (FDA) module that gates feature maps according to their energy distribution across wavelet sub-bands. WaveConvNeXt decomposes each feature map into four DWT sub-bands (LL, LH, HL, HH) at each stage, applies sub-band-specific convolutions to extract directional frequency features, and recombines them using learned FDA weights that adapt to the spatial frequency content of each input. We additionally propose a Wavelet Image Super-Resolution (WISR) decoder that leverages the preserved high-frequency sub-bands to reconstruct high-fidelity upsampled images as an auxiliary training signal. We evaluate WaveConvNeXt on three large-scale benchmarks: ImageNet-1K (1.28 million images, 1,000 classes), CIFAR-100 (60,000 images, 100 classes), and the DIV2K image super-resolution dataset (800 high-resolution training images). On ImageNet-1K, WaveConvNeXt-Base achieves 84.7% top-1 accuracy, surpassing ConvNeXt-V2-Base (83.7%) by 1.0% and Swin-Transformer-Base (83.5%) by 1.2%, with only 5.3% additional parameters. On CIFAR-100, WaveConvNeXt achieves 91.8% top-1 accuracy. On DIV2K ×4 super-resolution, WISR achieves PSNR of 33.24 dB and SSIM of 0.913, outperforming DRN and SwinIR baselines. Extensive ablation studies confirm that frequency-domain attention contributes +1.4% on ImageNet and +0.8% on CIFAR-100 over the ConvNeXt-V2 backbone alone.

Zitieren

APA

Ali, S. M. (2026). WaveConvNeXt: Wavelet-Guided Multi-Scale Feature Extraction with Frequency-Domain Attention for High-Fidelity Image Classification and Reconstruction. Journal of Computer Science Innovations and Research, 2(1), 21-31. https://doi.org/10.69055/jcsir.v2i1.8

Vancouver

Ali SM. WaveConvNeXt: Wavelet-Guided Multi-Scale Feature Extraction with Frequency-Domain Attention for High-Fidelity Image Classification and Reconstruction. Journal of Computer Science Innovations and Research. 2026;2(1):21-31. doi:10.69055/jcsir.v2i1.8

BibTeX
@article{Ali2026,
  author = {Ali, Saif Mohammed},
  title = {WaveConvNeXt: Wavelet-Guided Multi-Scale Feature Extraction with Frequency-Domain Attention for High-Fidelity Image Classification and Reconstruction},
  journal = {Journal of Computer Science Innovations and Research},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {21--31},
  doi = {10.69055/jcsir.v2i1.8}
}
Kostenlos starten →