Metraipolis › archive › dc_96bbcfde89a5

SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification — arXiv:2608.03631

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03631
License (as archived): CC0-1.0
Archived: 2026-10-31T12:59:43.712Z
SHA-256 of the archived text: 607784428ebefde1c907a14f19cc02875ad1913cd98528507e3c6d63ea03120b
Stable URL of this page: https://metraipolis.com/documento/dc_96bbcfde89a5

How to cite

SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification — arXiv:2608.03631 — arXiv (en), https://arxiv.org/abs/2608.03631 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96bbcfde89a5 (Metraipolis archive dc_96bbcfde89a5, sha256 607784428ebefde1c907a14f19cc02875ad1913cd98528507e3c6d63ea03120b)

BibTeX

@misc{dc96bbcfde89a5,
  title = {SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification — arXiv:2608.03631},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03631},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96bbcfde89a5; sha256 607784428ebefde1c907a14f19cc02875ad1913cd98528507e3c6d63ea03120b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03631. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatial relation questions require a model to identify the queried subject and object before comparing their layout. Yet a VLM can recognize both entities and still answer from the wrong instance or an ambiguous global view. We ask whether making query-specific evidence explicit can mitigate this failure and propose SEER (Self-grounded Evidence for Entity-Relation Reasoning), a training-free inference-time evidence interface for frozen VLMs. SEER hides candidate relations during pair localization, constructs a query-specific view with explicit subject/object roles, and retains the full image and sparse box geometry as complementary evidence. For relation-choice protocols with exact inverse support, an optional refinement swaps the entity roles and changes the forward decision only when exactly one visual state obeys the corresponding inverse relation. On an image-disjoint GQA-Train900 test frozen before model scoring, SEER pools to +3.94 [2.17,5.72] over Full; the gain remains positive under label-independent grounding-order counterbalancing and on the 535 rows whose entity names are unique. The unchanged protocol yields +4.35 to +11.79 on all 2,434 filtered EmbSpatial pair-relation questions across three models. Matched controls separate local refocus from role-explicit conditioning. These results establish query-specific evidence construction as the principal intervention, with reciprocal consistency as a smaller protocol-specific refinement.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03631 — 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 2026-10-31T12:45:33.264Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).