Metraipolis › archive › dc_69b3aae2bbda

Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation Leaderboard — arXiv:2609.38714

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38714
License (as archived): CC0-1.0
Archived: 2026-10-07T14:45:29.809Z
SHA-256 of the archived text: 9220e4159dd94ea394f173e319f84dbae9d5f1d80128ecadd14b288d7abe6834
Stable URL of this page: https://metraipolis.com/documento/dc_69b3aae2bbda

How to cite

Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation Leaderboard — arXiv:2609.38714 — arXiv (en), https://arxiv.org/abs/2609.38714 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69b3aae2bbda (Metraipolis archive dc_69b3aae2bbda, sha256 9220e4159dd94ea394f173e319f84dbae9d5f1d80128ecadd14b288d7abe6834)

BibTeX

@misc{dc69b3aae2bbda,
  title = {Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation Leaderboard — arXiv:2609.38714},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38714},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69b3aae2bbda; sha256 9220e4159dd94ea394f173e319f84dbae9d5f1d80128ecadd14b288d7abe6834},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38714. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We describe our winning entry to the Waymo Open Dataset 2D Video Panoptic Segmentation Challenge. The task asks for a semantic class at every pixel of every frame and, for countable objects, an identity that holds across 100 frames and across five overlapping cameras. We build on DVIS++, a cascade of a segmenter, a tracker, and a refiner, as our baseline. We propose hard region supervision (HRS) to improve the baseline. In particular, we use the baseline to define the hard region as where it makes mistakes, and design a loss and an auxiliary prediction head for this region. The auxiliary head is used only in training and removed at test time, so at inference the model trained with HRS has the same architecture as the baseline. In addition, we propose three test-time steps that further improve the results: a two-model ensemble, a merge of the segmenter's output into the final panoptic map, and cross-camera identity linking. On the challenge test set, our entry reaches 0.3547 wSTQ, 0.2071 wAQ, and 0.6075 mIoU, ranking first on all three metrics. It is 3.6 wSTQ points ahead of the second entry and 2.4 points ahead of our DVIS++ baseline.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.38714 — 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 2026-10-07T14:19:00.602Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).