# Tiny Object Detection with Single Point Supervision

arXiv: https://arxiv.org/abs/2412.05837 · HTML: https://mlsanity.com/paper/2412.05837/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 61 references that are in the map.
- First posted on arXiv 8 Dec 2024.

## Builds on (most cited first, 5 of 5)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [P2RBox: Point Prompt Oriented Object Detection with SAM](https://mlsanity.com/paper/2311.13128/) (2023)
- [Similarity Distance-Based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2407.02394/) (2024)
- [Robust Tiny Object Detection in Aerial Images amidst Label Noise](https://mlsanity.com/paper/2401.08056/) (2024)

## Built on by (most cited first, 2 of 2)

- [P2Object: Single Point Supervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2504.07813/) (2025)
- [Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark](https://mlsanity.com/paper/2604.02773/) (2026)

## Abstract (arXiv)

Tiny objects, with their limited spatial resolution, often resemble point-like distributions. As a result, bounding box prediction using point-level supervision emerges as a natural and cost-effective alternative to traditional box-level supervision. However, the small scale and lack of distinctive features of tiny objects make point annotations prone to noise, posing significant hurdles for model robustness. To tackle these challenges, we propose Point Teacher--the first end-to-end point-supervised method for robust tiny object detection in aerial images. To handle label noise from scale ambiguity and location shifts in point annotations, Point Teacher employs the teacher-student architecture and decouples the learning into a two-phase denoising process. In this framework, the teacher network progressively denoises the pseudo boxes derived from noisy point annotations, guiding the student network's learning. Specifically, in the first phase, random masking of image regions facilitates regression learning, enabling the teacher to transform noisy point annotations into coarse pseudo boxes. In the second phase, these coarse pseudo boxes are refined using dynamic multiple instance learning, which adaptively selects the most reliable instance from dynamically constructed proposal bags around the coarse pseudo boxes. Extensive experiments on three tiny object datasets (i.e., AI-TOD-v2, SODA-A, and TinyPerson) validate the proposed method's effectiveness and robustness against point location shifts. Notably, relying solely on point supervision, our Point Teacher already shows comparable performance with box-supervised learning methods. Codes and models will be made publicly available.