# Iterative Bounding Box Annotation for Object Detection

arXiv: https://arxiv.org/abs/2007.00961 · HTML: https://mlsanity.com/paper/2007.00961/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 15 of 15)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge](https://mlsanity.com/paper/2403.17420/) (2024)
- [Semi-Automatic Annotation For Visual Object Tracking](https://mlsanity.com/paper/2101.06977/) (2021)
- [Sample selection for efficient image annotation](https://mlsanity.com/paper/2105.04678/) (2021)
- [IAdet: Simplest human-in-the-loop object detection](https://mlsanity.com/paper/2307.01582/) (2023)
- [An Evaluation of Hybrid Annotation Workflows on High-Ambiguity Spatiotemporal Video Footage](https://mlsanity.com/paper/2510.21798/) (2025)
- [DIAGRAMS: A Review Framework for Reasoning-Level Attribution in Diagram QA](https://mlsanity.com/paper/2605.00905/) (2026)
- [Iterative Learning for Instance Segmentation](https://mlsanity.com/paper/2202.09110/) (2022)
- [Penalizing Proposals using Classifiers for Semi-Supervised Object Detection](https://mlsanity.com/paper/2205.13219/) (2022)
- [Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturing](https://mlsanity.com/paper/2206.00280/) (2022)
- [Self-Supervised learning for Neural Architecture Search (NAS)](https://mlsanity.com/paper/2304.01023/) (2023)
- [Feedback-driven object detection and iterative model improvement](https://mlsanity.com/paper/2411.19835/) (2024)
- [A Self-Supervised Approach for Enhanced Feature Representations in Object Detection Tasks](https://mlsanity.com/paper/2602.16322/) (2026)
- [Do Generative Metrics Predict YOLO Performance? An Evaluation Across Models, Augmentation Ratios, and Dataset Complexity](https://mlsanity.com/paper/2602.18525/) (2026)
- [From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review](https://mlsanity.com/paper/2605.12303/) (2026)

## Abstract (arXiv)

Manual annotation of bounding boxes for object detection in digital images is tedious, and time and resource consuming. In this paper, we propose a semi-automatic method for efficient bounding box annotation. The method trains the object detector iteratively on small batches of labeled images and learns to propose bounding boxes for the next batch, after which the human annotator only needs to correct possible errors. We propose an experimental setup for simulating the human actions and use it for comparing different iteration strategies, such as the order in which the data is presented to the annotator. We experiment on our method with three datasets and show that it can reduce the human annotation effort significantly, saving up to 75% of total manual annotation work.