# Training object class detectors with click supervision

arXiv: https://arxiv.org/abs/1704.06189 · HTML: https://mlsanity.com/paper/1704.06189/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2017.

## Built on by (most cited first, 11 of 11)

- [Omni-DETR: Omni-Supervised Object Detection with Transformers](https://mlsanity.com/paper/2203.16089/) (2022)
- [From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2412.11154/) (2024)
- [ExDDV: A New Dataset for Explainable Deepfake Detection in Video](https://mlsanity.com/paper/2503.14421/) (2025)
- [PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection](https://mlsanity.com/paper/2501.13898/) (2025)
- [A Lightweight Moment Retrieval System with Global Re-Ranking and Robust Adaptive Bidirectional Temporal Search](https://mlsanity.com/paper/2504.09298/) (2025)
- [LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision](https://mlsanity.com/paper/2509.22631/) (2025)
- [Assessing Domain Gap for Continual Domain Adaptation in Object Detection](https://mlsanity.com/paper/2302.10396/) (2023)
- [Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance](https://mlsanity.com/paper/2402.19401/) (2024)
- [The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration](https://mlsanity.com/paper/2502.01458/) (2025)
- [P2Object: Single Point Supervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2504.07813/) (2025)
- [Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding](https://mlsanity.com/paper/2610.19723/) (2026)

## Abstract (arXiv)

Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing center-click annotations: we ask annotators to click on the center of an imaginary bounding box which tightly encloses the object instance. We then incorporate these clicks into existing Multiple Instance Learning techniques for weakly supervised object localization, to jointly localize object bounding boxes over all training images. Extensive experiments on PASCAL VOC 2007 and MS COCO show that: (1) our scheme delivers high-quality detectors, performing substantially better than those produced by weakly supervised techniques, with a modest extra annotation effort; (2) these detectors in fact perform in a range close to those trained from manually drawn bounding boxes; (3) as the center-click task is very fast, our scheme reduces total annotation time by 9x to 18x.