Paper Detail

SADL: What to Ignore? A Benchmark for Subject-Aware Distractor Localization

Cao-Tri Nguyen, Nguyen-Khoa Luong, Vinh-Tiep Nguyen, Minh-Triet Tran

arxiv Score 15.8

Published 2026-06-29 · First seen 2026-06-30

General AI

Abstract

Photographs frequently contain \emph{visual distractors} besides foregrounds and backgrounds of the intended subject, competing for attention and weakening composition. While modern editing tools streamline object removal, identifying which objects to remove remains a mostly manual process. Existing saliency models and open-vocabulary detectors operate without subject awareness, failing to adapt to shifting user intent. Furthermore, context-agnostic removal may disrupt the scene's semantic coherence (e.g., keep the person but remove the chair they are sitting on). To address these limitations, we formalize the task of subject-aware distractor localization, which identifies distractors while retaining compositionally essential objects. This paper introduces \textsc{SADL}, the first real-world benchmark for this task, comprising 1,800 subject-aware cases across 1,000 photographs to enable systematic evaluation and facilitate future research. In total, there are 14,617 annotated candidates, including a robust set of 1,938 hard negatives to stress-test exclusion calibration. We evaluate seven proprietary and open-weight Vision-Language Models (VLMs) on a sequential pipeline of distractor classification followed by exclusion filtering, structured around five inclusion factors and three contextual exclusion rules. Our analysis reveals that VLMs are highly capable of identifying distractors, but then over-apply exclusion, which systematically suppresses true distractors at scale. By exposing this critical bottleneck, \textsc{SADL} provides a foundational diagnostic tool to advance subject-conditioned reasoning in multimodal systems.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{nguyen2026sadl,
  title = {SADL: What to Ignore? A Benchmark for Subject-Aware Distractor Localization},
  author = {Cao-Tri Nguyen and Nguyen-Khoa Luong and Vinh-Tiep Nguyen and Minh-Triet Tran},
  year = {2026},
  abstract = {Photographs frequently contain \textbackslash{}emph\{visual distractors\} besides foregrounds and backgrounds of the intended subject, competing for attention and weakening composition. While modern editing tools streamline object removal, identifying which objects to remove remains a mostly manual process. Existing saliency models and open-vocabulary detectors operate without subject awareness, failing to adapt to shifting user intent. Furthermore, context-agnostic removal may disrupt the scene's semantic coher},
  url = {https://arxiv.org/abs/2606.30393},
  keywords = {cs.CV},
  eprint = {2606.30393},
  archiveprefix = {arXiv},
}

Metadata

{}