Metraipolis › archive › dc_73b3cc708b26

LookThere! Sparse Vision by Reinforced Selection — arXiv:2609.04698

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04698
License (as archived)
CC0-1.0
Archived
2026-10-16T22:59:59.852Z
SHA-256 of the archived text
cb54abebc537649de70d3bf89420bee920645163f23eec47af86d7ab976c7a6e
Stable URL of this page
https://metraipolis.com/documento/dc_73b3cc708b26

How to cite

LookThere! Sparse Vision by Reinforced Selection — arXiv:2609.04698 — arXiv (en), https://arxiv.org/abs/2609.04698 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73b3cc708b26 (Metraipolis archive dc_73b3cc708b26, sha256 cb54abebc537649de70d3bf89420bee920645163f23eec47af86d7ab976c7a6e)
BibTeX
@misc{dc73b3cc708b26,
  title = {LookThere! Sparse Vision by Reinforced Selection — arXiv:2609.04698},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04698},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73b3cc708b26; sha256 cb54abebc537649de70d3bf89420bee920645163f23eec47af86d7ab976c7a6e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04698. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive computation methods accelerate inference by choosing which tokens to process, but existing methods struggle at extreme sparsity and require heuristics that may not generalize like token diversity and attention scores. We address these limitations with LookThere, achieving a new pareto frontier in performance-compute trade-offs through an end-to-end reinforcement learning framework that jointly trains a shallow input selector and a deep representation extractor. The selector learns where to look and the extractor learns what to see, together saving computation by selecting only what is worth processing for a given task without relying on auxiliary signals. We show that LookThere only selects the task-specific input, excelling at sparse recognition in high-resolution settings (traffic signs, billiards), and maintaining accuracy with as little as 0.2% of the input. It generalizes across tasks and models, including global recognition (ImageNet classification), local recognition (ADE20K segmentation), zero-shot classification (by distillation), and regression (counting). Across all settings, LookThere surpasses state-of-the-art selection to provide a general and scalable framework for specialized and efficient adaptive computation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.04698 — 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 2026-10-16T22:31:32.238Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).