# Hallucination In Object Detection -- A Study In Visual Part Verification

Source: [Hallucination In Object Detection -- A Study In Visual Part Verification](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea26184>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:16:37.291Z

Authors: Osman Semih Kayhan, Bart Vredebregt, Jan C. van Gemert

Published: 2021-06-04T14:47:11.000Z

## Abstract

We show that object detectors can hallucinate and detect missing objects; potentially even accurately localized at their expected, but non-existing, position. This is particularly problematic for applications that rely on visual part verification: detecting if an object part is present or absent. We show how popular object detectors hallucinate objects in a visual part verification task and introduce the first visual part verification dataset: DelftBikes, which has 10,000 bike photographs, with 22 densely annotated parts per image, where some parts may be missing. We explicitly annotated an extra object state label for each part to reflect if a part is missing or intact. We propose to evaluate visual part verification by relying on recall and compare popular object detectors on DelftBikes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.02523>)

[PDF](<https://arxiv.org/pdf/2106.02523.pdf>)
