# NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

arXiv: https://arxiv.org/abs/1812.00124 · HTML: https://mlsanity.com/paper/1812.00124/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2018.

## Built on by (most cited first, 30 of 37)

- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework](https://mlsanity.com/paper/2103.11402/) (2021)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving](https://mlsanity.com/paper/2106.11118/) (2021)
- [Decoupled Adaptation for Cross-Domain Object Detection](https://mlsanity.com/paper/2110.02578/) (2021)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [Omni-DETR: Omni-Supervised Object Detection with Transformers](https://mlsanity.com/paper/2203.16089/) (2022)
- [Visual Distant Supervision for Scene Graph Generation](https://mlsanity.com/paper/2103.15365/) (2021)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [Robust Object Detection With Inaccurate Bounding Boxes](https://mlsanity.com/paper/2207.09697/) (2022)
- [Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression](https://mlsanity.com/paper/2110.13675/) (2021)
- [Semi-supervised Open-World Object Detection](https://mlsanity.com/paper/2402.16013/) (2024)
- [Noisy Annotation Refinement for Object Detection](https://mlsanity.com/paper/2110.10456/) (2021)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [Semi-supervised Object Detection: A Survey on Recent Research and Progress](https://mlsanity.com/paper/2306.14106/) (2023)
- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [Sample Selection via Contrastive Fragmentation for Noisy Label Regression](https://mlsanity.com/paper/2502.17771/) (2025)
- [ZeroVO: Visual Odometry with Minimal Assumptions](https://mlsanity.com/paper/2506.08005/) (2025)
- [Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images](https://mlsanity.com/paper/2208.03327/) (2022)
- [Semi-Supervised and Long-Tailed Object Detection with CascadeMatch](https://mlsanity.com/paper/2305.14813/) (2023)
- [Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels](https://mlsanity.com/paper/2309.09742/) (2023)
- [Custom Object Detection via Multi-Camera Self-Supervised Learning](https://mlsanity.com/paper/2102.03442/) (2021)
- [Artificial intelligence for detection and quantification of rust and leaf miner in coffee crop](https://mlsanity.com/paper/2103.11241/) (2021)
- [Breast Mass Detection with Faster R-CNN: On the Feasibility of Learning from Noisy Annotations](https://mlsanity.com/paper/2104.12218/) (2021)

## Abstract (arXiv)

The labeling cost of large number of bounding boxes is one of the main challenges for training modern object detectors. To reduce the dependence on expensive bounding box annotations, we propose a new semi-supervised object detection formulation, in which a few seed box level annotations and a large scale of image level annotations are used to train the detector. We adopt a training-mining framework, which is widely used in weakly supervised object detection tasks. However, the mining process inherently introduces various kinds of labelling noises: false negatives, false positives and inaccurate boundaries, which can be harmful for training the standard object detectors (e.g. Faster RCNN). We propose a novel NOise Tolerant Ensemble RCNN (NOTE-RCNN) object detector to handle such noisy labels. Comparing to standard Faster RCNN, it contains three highlights: an ensemble of two classification heads and a distillation head to avoid overfitting on noisy labels and improve the mining precision, masking the negative sample loss in box predictor to avoid the harm of false negative labels, and training box regression head only on seed annotations to eliminate the harm from inaccurate boundaries of mined bounding boxes. We evaluate the methods on ILSVRC 2013 and MSCOCO 2017 dataset; we observe that the detection accuracy consistently improves as we iterate between mining and training steps, and state-of-the-art performance is achieved.