Metraipolis › archive › dc_2f5e56cdbbbd

Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection — arXiv:2608.04394

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04394
License (as archived): CC0-1.0
Archived: 2026-10-31T11:47:50.493Z
SHA-256 of the archived text: 22d4f1bdc7f55b57262453921a23d4944f38e03e4e67beb98b1ffae679a0281f
Stable URL of this page: https://metraipolis.com/documento/dc_2f5e56cdbbbd

How to cite

Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection — arXiv:2608.04394 — arXiv (en), https://arxiv.org/abs/2608.04394 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f5e56cdbbbd (Metraipolis archive dc_2f5e56cdbbbd, sha256 22d4f1bdc7f55b57262453921a23d4944f38e03e4e67beb98b1ffae679a0281f)

BibTeX

@misc{dc2f5e56cdbbbd,
  title = {Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection — arXiv:2608.04394},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04394},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f5e56cdbbbd; sha256 22d4f1bdc7f55b57262453921a23d4944f38e03e4e67beb98b1ffae679a0281f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04394. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cross-Domain Few-Shot Object Detection (CDFSOD) aims to transfer knowledge from data-rich upstream generic domains to downstream expert domains using scarce training data, where the significant domain gap and data scarcity make it an unsolved challenge. To address this problem, we revisit a natural yet underexplored approach in CDFSOD: data augmentation, by directly synthesizing data through diffusion models to supplement limited training samples. However, due to large domain gaps, we find that current diffusion methods cannot produce good results, leading to performance even lower than using the original images. To address these limitations, we divide the domain gaps into visual gaps and semantic gaps for separate analysis. For the visual gap, we find that the diffusion model cannot distinguish noise from useful information on expert domains, which can be mitigated by adding weakened noise. For the semantic gap, we find that the background semantics shows much smaller gaps between domains than foreground semantics, and we can bridge this gap by background inpainting. Based on the above analysis, we propose a method (Selective Inpainting with Tailored Noise, SITN) to dynamically take different strategies for downstream data synthesis based on their different gaps from the general domain, including a Generation Module for adding tailored noise and a Selection Module to dynamically select the inpainting regions. Extensive experiments on 6 datasets of CDFSOD and 4 datasets of cross-domain few-shot segmentation (CDFSS) validate that we can synthesize helpful data, achieving new state-of-the-art performance. Our codes is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.04394 — 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 2026-10-31T11:37:40.659Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).