Metraipolis › archive › dc_2ee67c21f0ce

Cross-Modal Knowledge Distillation for Acoustic Pedestrian Detection — arXiv:2609.31785

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31785
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:28.409Z
SHA-256 of the archived text
6fc6f6a506ed2e82c5559dcf3db9fd7dc01243c1ea893a46dd682720b34a3c11
Stable URL of this page
https://metraipolis.com/documento/dc_2ee67c21f0ce

How to cite

Cross-Modal Knowledge Distillation for Acoustic Pedestrian Detection — arXiv:2609.31785 — arXiv (en), https://arxiv.org/abs/2609.31785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ee67c21f0ce (Metraipolis archive dc_2ee67c21f0ce, sha256 6fc6f6a506ed2e82c5559dcf3db9fd7dc01243c1ea893a46dd682720b34a3c11)
BibTeX
@misc{dc2ee67c21f0ce,
  title = {Cross-Modal Knowledge Distillation for Acoustic Pedestrian Detection — arXiv:2609.31785},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31785},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ee67c21f0ce; sha256 6fc6f6a506ed2e82c5559dcf3db9fd7dc01243c1ea893a46dd682720b34a3c11},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Audio-only pedestrian detection is attractive for urban sensing but limited by weak acoustic cues. An appealing strategy is cross-modal knowledge distillation, in which a video teacher supervises the audio student during training so that the deployed model runs on audio alone. Under this task's severe class imbalance and wide video-audio modality gap, however, what such distillation contributes is unclear. We introduce Trust-Filtered Distillation (TFD), which selectively suppresses teacher supervision on pedestrian samples, and interpret its logit formulation as conditional label smoothing under a shared temperature. Across ten distillation configurations under five-fold cross-session validation on ASPED, most methods yield modest gains in macro accuracy accompanied by small changes in PR-AUC. The main effect is higher no-pedestrian accuracy at the cost of lower pedestrian recall. Adding TFD to logit distillation strengthens this trade-off without improving mean PR-AUC. These findings clarify the benefits and limitations of selective cross-modal supervision by distinguishing operating-point shifts from discrimination gains in imbalanced acoustic detection.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.31785 — 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 2026-10-07T22:14:28.545Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).