{
  "annotation_id": "46ebeafc-4f1e-419c-827e-75ec8c6d7ead",
  "date_created": "2026-02-17T05:53:15.301000Z",
  "date_modified": "2026-02-17T05:53:15.301000Z",
  "file_hash": "67e833dfb980efc0d009010557179a46ddd56834dc8fe7a0be5d5d9b5b463904",
  "private": false,
  "record": {
    "abstract": "Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address this issue by implementing debiasing strategies, but often at the cost of spatial understanding, resulting in an over-reliance on semantic priors. We introduce Salience-SGG, a novel framework featuring an Iterative Salience Decoder (ISD) that emphasizes triplets with salient spatial structures. To support this, we propose semantic-agnostic salience labels guiding ISD. Evaluations on Visual Genome, Open Images V6, and GQA-200 show that Salience-SGG achieves state-of-the-art performance and improves existing Unbiased-SGG methods in their spatial understanding as demonstrated by the Pairwise Localization Average Precision",
    "arxiv_id": "2601.08728",
    "authors": [
      "Runfeng Qu",
      "Ole Hall",
      "Pia K Bideau",
      "Julie Ouerfelli-Ethier",
      "Martin Rolfs",
      "Klaus Obermayer",
      "Olaf Hellwich"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation",
    "url": "https://arxiv.org/abs/2601.08728",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "08293c10-8e7c-41d7-8745-8ba27f7937e5",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}