# Solving Missing-Annotation Object Detection with Background Recalibration Loss

arXiv: https://arxiv.org/abs/2002.05274 · HTML: https://mlsanity.com/paper/2002.05274/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 27 of 27)

- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [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)
- [Adaptive Self-training Framework for Fine-grained Scene Graph Generation](https://mlsanity.com/paper/2401.09786/) (2024)
- [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)
- [Multispectral Pedestrian Detection with Sparsely Annotated Label](https://mlsanity.com/paper/2501.02640/) (2025)
- [Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images](https://mlsanity.com/paper/2208.03327/) (2022)
- [CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles](https://mlsanity.com/paper/2111.08243/) (2021)
- [Semi-Supervised and Long-Tailed Object Detection with CascadeMatch](https://mlsanity.com/paper/2305.14813/) (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)
- [GlideNet: Global, Local and Intrinsic based Dense Embedding NETwork for Multi-category Attributes Prediction](https://mlsanity.com/paper/2203.03079/) (2022)
- [Hierarchy exploitation to detect missing annotations on hierarchical multi-label classification](https://mlsanity.com/paper/2207.06237/) (2022)
- [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)
- [Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation](https://mlsanity.com/paper/2505.14239/) (2025)
- [Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baseline](https://mlsanity.com/paper/2606.09219/) (2026)
- [TagMe: GPS-Assisted Automatic Object Annotation in Videos](https://mlsanity.com/paper/2103.13428/) (2021)
- [ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers](https://mlsanity.com/paper/2209.05654/) (2022)
- [Read, look and detect: Bounding box annotation from image-caption pairs](https://mlsanity.com/paper/2306.06149/) (2023)
- [Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection](https://mlsanity.com/paper/2311.00278/) (2023)
- [Anno-incomplete Multi-dataset Detection](https://mlsanity.com/paper/2408.16247/) (2024)
- [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)

This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this problem has proposed to use soft sampling to re-weight the gradients of RoIs based on the overlaps with positive instances, while their method is mainly based on the two-stage detector (i.e. Faster RCNN) which is more robust and friendly for the missing label scenario. In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image. Our design is built on the one-stage detector which is faster and lighter. Inspired by the Focal Loss formulation, we make several significant modifications to fit on the missing-annotation circumstance. We conduct extensive experiments on the curated PASCAL VOC and MS COCO datasets. The results demonstrate that our proposed method outperforms the baseline and other state-of-the-arts by a large margin. Code available: https://github.com/Dwrety/mmdetection-selective-iou.