# Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection

arXiv: https://arxiv.org/abs/2012.01950 · HTML: https://mlsanity.com/paper/2012.01950/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 29 of 29)

- [Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learning](https://mlsanity.com/paper/2205.15948/) (2022)
- [SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining](https://mlsanity.com/paper/2201.04620/) (2022)
- [Box-Level Active Detection](https://mlsanity.com/paper/2303.13089/) (2023)
- [SIOD: Single Instance Annotated Per Category Per Image for Object Detection](https://mlsanity.com/paper/2203.15353/) (2022)
- [Calibrated Teacher for Sparsely Annotated Object Detection](https://mlsanity.com/paper/2303.07582/) (2023)
- [Scaling up instance annotation via label propagation](https://mlsanity.com/paper/2110.02277/) (2021)
- [Multispectral Pedestrian Detection with Sparsely Annotated Label](https://mlsanity.com/paper/2501.02640/) (2025)
- [Bootstrap Your Object Detector via Mixed Training](https://mlsanity.com/paper/2111.03056/) (2021)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [Semi-Supervised and Long-Tailed Object Detection with CascadeMatch](https://mlsanity.com/paper/2305.14813/) (2023)
- [Universal Noise Annotation: Unveiling the Impact of Noisy annotation on Object Detection](https://mlsanity.com/paper/2312.13822/) (2023)
- [Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?](https://mlsanity.com/paper/2403.02818/) (2024)
- [LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection](https://mlsanity.com/paper/2509.16970/) (2025)
- [Semi-supervised Cell Detection in Time-lapse Images Using Temporal Consistency](https://mlsanity.com/paper/2107.08639/) (2021)
- [Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)](https://mlsanity.com/paper/2210.12989/) (2022)
- [Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Images](https://mlsanity.com/paper/2306.15898/) (2023)
- [Tackling the Incomplete Annotation Issue in Universal Lesion Detection Task By Exploratory Training](https://mlsanity.com/paper/2309.13306/) (2023)
- [Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking](https://mlsanity.com/paper/2403.02495/) (2024)
- [Leveraging Sparse Annotations for Leukemia Diagnosis on the Large Leukemia Dataset](https://mlsanity.com/paper/2504.02602/) (2025)
- [MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label](https://mlsanity.com/paper/2604.01646/) (2026)
- [Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark](https://mlsanity.com/paper/2604.02773/) (2026)
- [Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baseline](https://mlsanity.com/paper/2606.09219/) (2026)
- [TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2607.08201/) (2026)
- [Read, look and detect: Bounding box annotation from image-caption pairs](https://mlsanity.com/paper/2306.06149/) (2023)
- [Utilizing Grounded SAM for self-supervised frugal camouflaged human detection](https://mlsanity.com/paper/2406.05776/) (2024)
- [Anno-incomplete Multi-dataset Detection](https://mlsanity.com/paper/2408.16247/) (2024)
- [S2Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection](https://mlsanity.com/paper/2504.11111/) (2025)
- [SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection](https://mlsanity.com/paper/2602.03634/) (2026)
- [Towards Sparsely Annotated Open-World Object Detection](https://mlsanity.com/paper/2608.12714/) (2026)

## Abstract (arXiv)

Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated object detection either re-weight the loss of hard negative samples or convert the unlabeled instances into ignored regions to reduce the interference of false negatives. We argue that these strategies are insufficient since they can at most alleviate the negative effect caused by missing annotations. In this paper, we propose a simple but effective mechanism, called Co-mining, for sparsely annotated object detection. In our Co-mining, two branches of a Siamese network predict the pseudo-label sets for each other. To enhance multi-view learning and better mine unlabeled instances, the original image and corresponding augmented image are used as the inputs of two branches of the Siamese network, respectively. Co-mining can serve as a general training mechanism applied to most of modern object detectors. Experiments are performed on MS COCO dataset with three different sparsely annotated settings using two typical frameworks: anchor-based detector RetinaNet and anchor-free detector FCOS. Experimental results show that our Co-mining with RetinaNet achieves 1.4%~2.1% improvements compared with different baselines and surpasses existing methods under the same sparsely annotated setting. Code is available at https://github.com/megvii-research/Co-mining.