Metraipolis › archive › dc_1bd82cdbaa42

TopoMix: Continuous Spatial Mixing for Long-Tailed Data Augmentation — arXiv:2611.00047

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00047
License (as archived)
CC0-1.0
Archived
2026-11-03T18:52:54.392Z
SHA-256 of the archived text
1c362244e0c12648ab94acda9d165497c3aaee6a07f8d7743a50b96883461453
Stable URL of this page
https://metraipolis.com/documento/dc_1bd82cdbaa42

How to cite

TopoMix: Continuous Spatial Mixing for Long-Tailed Data Augmentation — arXiv:2611.00047 — arXiv (en), https://arxiv.org/abs/2611.00047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1bd82cdbaa42 (Metraipolis archive dc_1bd82cdbaa42, sha256 1c362244e0c12648ab94acda9d165497c3aaee6a07f8d7743a50b96883461453)
BibTeX
@misc{dc1bd82cdbaa42,
  title = {TopoMix: Continuous Spatial Mixing for Long-Tailed Data Augmentation — arXiv:2611.00047},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00047},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1bd82cdbaa42; sha256 1c362244e0c12648ab94acda9d165497c3aaee6a07f8d7743a50b96883461453},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most mixing-based augmentation methods improve generalization through a simple idea: combine two training samples with a fixed global ratio or a hard spatial replacement. While effective, this design leaves little room for local variation, which becomes a more visible limitation in long-tailed recognition, where minority classes are especially sensitive to the quality of augmented samples. We propose TopoMix, a training-free augmentation method that replaces fixed mixing with continuous spatial mixing. TopoMix constructs a smooth spatially varying mask from a low-resolution random control grid, bicubic interpolation, and stochastic non-linear shaping, and uses this mask for element-wise image mixing and label reweighting. Without introducing trainable parameters or auxiliary networks, TopoMix offers a simple way to make mixing more flexible in the input space. Experiments on standard long-tailed benchmarks show that it consistently improves over representative mixing-based baselines, indicating that smooth spatial mixing is an effective augmentation strategy for long-tailed recognition.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00047 — 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 2026-11-03T18:16:52.838Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).