# SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining

arXiv: https://arxiv.org/abs/2201.04620 · HTML: https://mlsanity.com/paper/2201.04620/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 12 Jan 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [An Analysis of Scale Invariance in Object Detection - SNIP](https://mlsanity.com/paper/1711.08189/) (2017)
- [SNIPER: Efficient Multi-Scale Training](https://mlsanity.com/paper/1805.09300/) (2018)
- [Toward unsupervised, multi-object discovery in large-scale image collections](https://mlsanity.com/paper/2007.02662/) (2020)
- [Proposal Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2001.05086/) (2020)
- [AutoFocus: Efficient Multi-Scale Inference](https://mlsanity.com/paper/1812.01600/) (2018)
- [Unsupervised Image Matching and Object Discovery as Optimization](https://mlsanity.com/paper/1904.03148/) (2019)
- [Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CT](https://mlsanity.com/paper/2009.02577/) (2020)
- [Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection](https://mlsanity.com/paper/2012.01950/) (2020)
- [Solving Missing-Annotation Object Detection with Background Recalibration Loss](https://mlsanity.com/paper/2002.05274/) (2020)
- [Towards Noise-resistant Object Detection with Noisy Annotations](https://mlsanity.com/paper/2003.01285/) (2020)
- [Soft Sampling for Robust Object Detection](https://mlsanity.com/paper/1806.06986/) (2018)

## Built on by (most cited first, 14 of 14)

- [Box-Level Active Detection](https://mlsanity.com/paper/2303.13089/) (2023)
- [Multispectral Pedestrian Detection with Sparsely Annotated Label](https://mlsanity.com/paper/2501.02640/) (2025)
- [FD-SOS: Vision-Language Open-Set Detectors for Bone Fenestration and Dehiscence Detection from Intraoral Images](https://mlsanity.com/paper/2407.09088/) (2024)
- [LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection](https://mlsanity.com/paper/2509.16970/) (2025)
- [Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)](https://mlsanity.com/paper/2210.12989/) (2022)
- [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)
- [Utilization of Neighbor Information for Image Classification with Different Levels of Supervision](https://mlsanity.com/paper/2503.14500/) (2025)
- [SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection](https://mlsanity.com/paper/2602.03634/) (2026)
- [Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2603.06374/) (2026)
- [Towards Sparsely Annotated Open-World Object Detection](https://mlsanity.com/paper/2608.12714/) (2026)
- [Background-Free Objectness Learning for Class-Agnostic Detection](https://mlsanity.com/paper/2608.29232/) (2026)

## Abstract (arXiv)

Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that existing methods suffer at higher levels of sparsity in the data due to noisy pseudo-labels. To prevent this, we propose an end-to-end system that learns to separate the proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions thereby preventing the negative effects of noisy pseudo-labels. This novel approach has multiple advantages such as improved robustness to higher sparsity when compared to existing methods. We conduct exhaustive experiments on five splits on the PASCAL-VOC and COCO datasets achieving state-of-the-art performance. We also unify various splits used across literature for this task and present a standardized benchmark. On average, we improve by 2.6, 3.9 and 9.6 mAP over previous state-of-the-art methods on three splits of increasing sparsity on COCO. Our project is publicly available at https://www.cs.umd.edu/~sakshams/SparseDet.