Metraipolis › archive › dc_b7eb3ac313ad

FD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectors — arXiv:2608.18590

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18590
License (as archived)
CC0-1.0
Archived
2026-10-18T14:06:17.614Z
SHA-256 of the archived text
6338a1d17b6195b7822d9ac18c0b3d3af660ed9463416040aedd28b1595a7120
Stable URL of this page
https://metraipolis.com/documento/dc_b7eb3ac313ad

How to cite

FD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectors — arXiv:2608.18590 — arXiv (en), https://arxiv.org/abs/2608.18590 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b7eb3ac313ad (Metraipolis archive dc_b7eb3ac313ad, sha256 6338a1d17b6195b7822d9ac18c0b3d3af660ed9463416040aedd28b1595a7120)
BibTeX
@misc{dcb7eb3ac313ad,
  title = {FD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectors — arXiv:2608.18590},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18590},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b7eb3ac313ad; sha256 6338a1d17b6195b7822d9ac18c0b3d3af660ed9463416040aedd28b1595a7120},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18590. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Compact object detectors are suitable for resource-constrained visual perception, but their limited representation capacity creates an accuracy gap relative to large models. Conventional detector distillation often relies on prediction-level supervision or a single feature-alignment target, such as response, distribution, correlation, or frequency-domain matching. Frequency-Decoupled Cross-Attention Knowledge Distillation (FD-CanKD) is presented as a detector-oriented framework that transfers teacher knowledge at three complementary levels: head-level prediction supervision, relation-level non-local context transfer, and frequency-level component-selective alignment. Student features first aggregate teacher-side spatial context through cross-attention-based relation transfer, after which frequency-aware alignment preserves complementary structural and detail-sensitive cues. Under controlled Microsoft Common Objects in Context (COCO) experiments, fixed 50-epoch from-scratch comparisons show that FD-CanKD remains competitive with representative detector knowledge distillation baselines. Post-distillation continued fine-tuning further produces a stronger refinement-ready student than detector-only fine-tuning, reaching 48.87 mean average precision (mAP) at intersection-over-union thresholds from 0.50 to 0.95 (mAP50:95), 65.84 mAP50, and 53.40 mAP75 after 20 additional epochs. All distillation modules are removed after training, leaving the deployed student unchanged at 19.7M parameters. The framework is instantiated and evaluated in a controlled YOLOv12 teacher-student setting as a representative compact-detector case study.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.18590 — 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 2026-10-18T14:00:22.557Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).