Metraipolis › archive › dc_7387fa670cd8

Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation — arXiv:2610.20881

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.20881
License (as archived): CC0-1.0
Archived: 2026-10-16T10:25:02.685Z
SHA-256 of the archived text: 00b415dcd0f9fc6f669a55cb119b0812d45153cddd08f72b45d357e8adec1dda
Stable URL of this page: https://metraipolis.com/documento/dc_7387fa670cd8

How to cite

Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation — arXiv:2610.20881 — arXiv (en), https://arxiv.org/abs/2610.20881 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7387fa670cd8 (Metraipolis archive dc_7387fa670cd8, sha256 00b415dcd0f9fc6f669a55cb119b0812d45153cddd08f72b45d357e8adec1dda)

BibTeX

@misc{dc7387fa670cd8,
  title = {Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation — arXiv:2610.20881},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20881},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7387fa670cd8; sha256 00b415dcd0f9fc6f669a55cb119b0812d45153cddd08f72b45d357e8adec1dda},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20881. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the patch or region level, where annotation requirements remain high due to extensive pixel labeling. Extending ViT-based AL to the pixel-level, low-budget regime is uniquely challenging: with as little as one pixel query per image, a method must simultaneously identify the most informative locations and train a reliable decoder head from an extremely sparse signal. We introduce TEAL (Token-space Efficient Active Learning), the first pixel-level AL framework built around ViT representations. TEAL uses a frozen ViT backbone and performs diversity-based selection directly on its native token lattice, avoiding the artifacts introduced by interpolating token embeddings to dense pixel resolutions. Our framework applies a two-level MaxHerding strategy over multi-layer token descriptors to select representative candidates, followed by margin-based uncertainty refinement on a finer decoder grid. Across CamVid, Cityscapes, ADE20K, and Pascal Context, TEAL consistently outperforms previous baselines under extreme label scarcity, improving over the strongest baseline by up to +24.36 mIoU with a single labeled pixel (px) per image, and reaching up to 97% of fully supervised performance with just 10 px. To rigorously establish the source of the gains, we further show that the improvements persist when all baselines are equipped with the same DINOv3 backbone, demonstrating that coupling token-space selection with uncertainty refinement on the decoder grid makes ViT token geometry an effective foundation for extremely low-budget active segmentation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.20881 — 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 2026-10-16T08:48:02.855Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).