# Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection

arXiv: https://arxiv.org/abs/2209.01589 · HTML: https://mlsanity.com/paper/2209.01589/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 4 Sep 2022.

## Builds on (most cited first, 30 of 38)

- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [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)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [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)
- [AutoAssign: Differentiable Label Assignment for Dense Object Detection](https://mlsanity.com/paper/2007.03496/) (2020)
- [FreeAnchor: Learning to Match Anchors for Visual Object Detection](https://mlsanity.com/paper/1909.02466/) (2019)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [Factorizing Knowledge in Neural Networks](https://mlsanity.com/paper/2207.03337/) (2022)
- [PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection](https://mlsanity.com/paper/2203.16317/) (2022)
- [Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2103.16368/) (2021)
- [Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection](https://mlsanity.com/paper/2207.02541/) (2022)

## Built on by (most cited first, 30 of 43)

- [Diverse Cotraining Makes Strong Semi-Supervised Segmentor](https://mlsanity.com/paper/2308.09281/) (2023)
- [AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.17373/) (2024)
- [Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?](https://mlsanity.com/paper/2312.04548/) (2023)
- [Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection](https://mlsanity.com/paper/2404.01819/) (2024)
- [SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection](https://mlsanity.com/paper/2407.01016/) (2024)
- [VideoOrion: Tokenizing Object Dynamics in Videos](https://mlsanity.com/paper/2411.16156/) (2024)
- [Vision Language Models See What You Want but not What You See](https://mlsanity.com/paper/2410.00324/) (2024)
- [BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation](https://mlsanity.com/paper/2403.15019/) (2024)
- [Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment](https://mlsanity.com/paper/2407.19675/) (2024)
- [Probing Perceptual Constancy in Large Vision-Language Models](https://mlsanity.com/paper/2502.10273/) (2025)
- [Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images](https://mlsanity.com/paper/2310.05498/) (2023)
- [STAT: Towards Generalizable Temporal Action Localization](https://mlsanity.com/paper/2404.13311/) (2024)
- [Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation](https://mlsanity.com/paper/2405.11754/) (2024)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Vision Language Models Know Law of Conservation without Understanding More-or-Less](https://mlsanity.com/paper/2410.00332/) (2024)
- [Enhancing cross-domain detection: adaptive class-aware contrastive transformer](https://mlsanity.com/paper/2401.13264/) (2024)
- [Partial Weakly-Supervised Oriented Object Detection](https://mlsanity.com/paper/2507.02751/) (2025)
- [LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection](https://mlsanity.com/paper/2303.05739/) (2023)
- [SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting](https://mlsanity.com/paper/2504.09966/) (2025)
- [LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection](https://mlsanity.com/paper/2509.16970/) (2025)
- [CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels](https://mlsanity.com/paper/2603.21071/) (2026)
- [Towards Understanding Adversarial Transferability in Federated Learning](https://mlsanity.com/paper/2310.00616/) (2023)
- [SSF3D: Strict Semi-Supervised 3D Object Detection with Switching Filter](https://mlsanity.com/paper/2403.17390/) (2024)
- [SemiHMER: Semi-supervised Handwritten Mathematical Expression Recognition using pseudo-labels](https://mlsanity.com/paper/2502.07172/) (2025)
- [CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization](https://mlsanity.com/paper/2502.16809/) (2025)
- [ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection](https://mlsanity.com/paper/2503.02897/) (2025)
- [Practical Insights into Semi-Supervised Object Detection Approaches](https://mlsanity.com/paper/2601.13380/) (2026)
- [Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark](https://mlsanity.com/paper/2604.02773/) (2026)
- [STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection](https://mlsanity.com/paper/2605.20738/) (2026)
- [Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization](https://mlsanity.com/paper/2606.31373/) (2026)

## Abstract (arXiv)

In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD). Our core observation is that the oscillating pseudo-targets undermine the training of an accurate detector. It injects noise into the student's training, leading to severe overfitting problems. Therefore, we propose a systematic solution, termed ConsistentTeacher, to reduce the inconsistency. First, adaptive anchor assignment~(ASA) substitutes the static IoU-based strategy, which enables the student network to be resistant to noisy pseudo-bounding boxes. Then we calibrate the subtask predictions by designing a 3D feature alignment module~(FAM-3D). It allows each classification feature to adaptively query the optimal feature vector for the regression task at arbitrary scales and locations. Lastly, a Gaussian Mixture Model (GMM) dynamically revises the score threshold of pseudo-bboxes, which stabilizes the number of ground truths at an early stage and remedies the unreliable supervision signal during training. ConsistentTeacher provides strong results on a large range of SSOD evaluations. It achieves 40.0 mAP with ResNet-50 backbone given only 10% of annotated MS-COCO data, which surpasses previous baselines using pseudo labels by around 3 mAP. When trained on fully annotated MS-COCO with additional unlabeled data, the performance further increases to 47.7 mAP. Our code is available at urlhttps://github.com/Adamdad/ConsistentTeacher.