# MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection

arXiv: https://arxiv.org/abs/2111.10958 · HTML: https://mlsanity.com/paper/2111.10958/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 22 Nov 2021.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 34)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework](https://mlsanity.com/paper/2103.11402/) (2021)
- [Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer](https://mlsanity.com/paper/1807.07543/) (2018)

## Built on by (most cited first, 21 of 21)

- [Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.00673/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection](https://mlsanity.com/paper/2207.05536/) (2022)
- [Dynamic Curriculum Learning for Great Ape Detection in the Wild](https://mlsanity.com/paper/2205.00275/) (2022)
- [Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels](https://mlsanity.com/paper/2312.01169/) (2023)
- [Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting](https://mlsanity.com/paper/2207.05334/) (2022)
- [Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty](https://mlsanity.com/paper/2212.02747/) (2022)
- [Semi-supervised Object Detection: A Survey on Recent Research and Progress](https://mlsanity.com/paper/2306.14106/) (2023)
- [Adaptive Self-Training for Object Detection](https://mlsanity.com/paper/2212.05911/) (2022)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation](https://mlsanity.com/paper/2203.07837/) (2022)
- [Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving](https://mlsanity.com/paper/2210.08748/) (2022)
- [Infinite Class Mixup](https://mlsanity.com/paper/2305.10293/) (2023)
- [Semi-Supervised Unconstrained Head Pose Estimation in the Wild](https://mlsanity.com/paper/2404.02544/) (2024)
- [Training-based Model Refinement and Representation Disagreement for Semi-Supervised Object Detection](https://mlsanity.com/paper/2307.13755/) (2023)
- [IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks](https://mlsanity.com/paper/2404.16331/) (2024)
- [Low-Confidence Samples Mining for Semi-supervised Object Detection](https://mlsanity.com/paper/2306.16201/) (2023)
- [Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Images](https://mlsanity.com/paper/2310.14718/) (2023)
- [Collaboration of Teachers for Semi-supervised Object Detection](https://mlsanity.com/paper/2405.13374/) (2024)
- [P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2505.15861/) (2025)
- [DDS-UDA: Dual-Domain Synergy for Unsupervised Domain Adaptation in Joint Segmentation of Optic Disc and Optic Cup](https://mlsanity.com/paper/2603.13345/) (2026)

## Abstract (arXiv)

Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant role in the SSL framework since it is hard to create a weak-strong augmented input pair without losing label information. Especially when extending SSL to semi-supervised object detection (SSOD), many strong augmentation methodologies related to image geometry and interpolation-regularization are hard to utilize since they possibly hurt the location information of the bounding box in the object detection task. To address this, we introduce a simple yet effective data augmentation method, Mix/UnMix (MUM), which unmixes feature tiles for the mixed image tiles for the SSOD framework. Our proposed method makes mixed input image tiles and reconstructs them in the feature space. Thus, MUM can enjoy the interpolation-regularization effect from non-interpolated pseudo-labels and successfully generate a meaningful weak-strong pair. Furthermore, MUM can be easily equipped on top of various SSOD methods. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate the superiority of MUM by consistently improving the mAP performance over the baseline in all the tested SSOD benchmark protocols.