Metraipolis › archive › dc_795e2ca85b0a

Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification — arXiv:2610.04073

Source
arXiv
Original
https://arxiv.org/abs/2610.04073
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:59.684Z
SHA-256 of the archived text
c533465aed85ea3a5c73aef2990742937c3274eb9c9571add38b2eca0da6ad5f
Stable URL of this page
https://metraipolis.com/documento/dc_795e2ca85b0a

How to cite

Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification — arXiv:2610.04073 — arXiv, https://arxiv.org/abs/2610.04073 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_795e2ca85b0a (Metraipolis archive dc_795e2ca85b0a, sha256 c533465aed85ea3a5c73aef2990742937c3274eb9c9571add38b2eca0da6ad5f)
BibTeX
@misc{dc795e2ca85b0a,
  title = {Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification — arXiv:2610.04073},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04073},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_795e2ca85b0a; sha256 c533465aed85ea3a5c73aef2990742937c3274eb9c9571add38b2eca0da6ad5f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04073. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in attention-based deep learning have motivated their adoption for remote sensing image classification; however, their benefits for cryospheric imagery, where surface states are dominated by fine-grained textures and class imbalance, remain unclear. In this work, we revisit a benchmark Greenland Ice Sheet image dataset, previously shown to favor convolutional neural networks (CNNs), to examine whether modern attention-based and hybrid architectures improve class-wise reliability. We conduct a controlled comparison between a classical CNN (AlexNet), a modern CNN (ConvNeXt-Tiny), a pure attention-based model (Swin-Tiny), and a hybrid convolution-attention model (CoAtNet-0) under identical training and evaluation protocols. Results show that AlexNet achieves the highest accuracy and the strongest balanced performance as measured by macro-averaged F1, while ConvNeXt-Tiny exhibits the highest macro-averaged AUC, indicating strong class separability but less consistent final decision quality. Class-wise analysis reveals that hybrid architectures improve recall for rare and structurally distinct surface classes, whereas convolutional models remain more reliable for texture-dominated categories. These findings highlight the importance of aligning architectural inductive bias with cryospheric data characteristics and suggest that increased model complexity does not necessarily translate to improved reliability for ice-sheet surface classification.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04073 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:27:05.942Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).