Pith. sign in

REVIEW 3 cited by

RePOPE: Impact of Annotation Errors on the POPE Benchmark

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.15707 v1 pith:IS52YJGM submitted 2025-04-22 cs.CV cs.AIcs.LG

RePOPE: Impact of Annotation Errors on the POPE Benchmark

classification cs.CV cs.AIcs.LG
keywords benchmarkannotationerrorsimpactrepopedatadatasetslabel
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Since data annotation is costly, benchmark datasets often incorporate labels from established image datasets. In this work, we assess the impact of label errors in MSCOCO on the frequently used object hallucination benchmark POPE. We re-annotate the benchmark images and identify an imbalance in annotation errors across different subsets. Evaluating multiple models on the revised labels, which we denote as RePOPE, we observe notable shifts in model rankings, highlighting the impact of label quality. Code and data are available at https://github.com/YanNeu/RePOPE .

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability

    cs.AI 2026-05 unverdicted novelty 7.0

    Introduces Synergistic Faithfulness metric based on Shapley Interaction Index to evaluate cross-modal synergy in VLM explainers, revealing over-reliance on visual salience in existing methods.

  2. A Good Initialization is All You Need for Faithful Visual Attribution

    cs.CV 2026-07 conditional novelty 6.0

    TRACE’s fixed-k cross-entropy mask search and COPAIR’s coarse-pair warm-start raise search-based visual attribution faithfulness and enable high single-point RePOPE repair rates.

  3. Diagnosing Visual Ignorance in Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    VLMs show language-prior reliance via multi-stage bottlenecks in visual retrieval and suppression, with many benchmark examples remaining answerable under severe visual obfuscation.