# DMT: Dynamic Mutual Training for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2004.08514 · HTML: https://mlsanity.com/paper/2004.08514/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2020.

## Built on by (most cited first, 30 of 77)

- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank](https://mlsanity.com/paper/2104.13415/) (2021)
- [Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.09025/) (2021)
- [Bootstrapping Semantic Segmentation with Regional Contrast](https://mlsanity.com/paper/2104.04465/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2212.04976/) (2022)
- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2205.10334/) (2022)
- [SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance](https://mlsanity.com/paper/2311.16241/) (2023)
- [Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant](https://mlsanity.com/paper/2301.07340/) (2023)
- [Generative Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2207.10015/) (2022)
- [Self-Adversarial Disentangling for Specific Domain Adaptation](https://mlsanity.com/paper/2108.03553/) (2021)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data](https://mlsanity.com/paper/2303.11066/) (2023)
- [Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2108.12545/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Decoder Denoising Pretraining for Semantic Segmentation](https://mlsanity.com/paper/2205.11423/) (2022)
- [Test-Time Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2403.19334/) (2024)
- [Fuzzy Positive Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2210.08519/) (2022)
- [A Survey on Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.09899/) (2023)
- [Semantic Segmentation with Active Semi-Supervised Learning](https://mlsanity.com/paper/2203.10730/) (2022)
- [Rethinking Domain Generalization: Discriminability and Generalizability](https://mlsanity.com/paper/2309.16483/) (2023)
- [Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2403.06462/) (2024)
- [Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2211.16701/) (2022)
- [BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model](https://mlsanity.com/paper/2401.02317/) (2024)
- [Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling](https://mlsanity.com/paper/2108.06649/) (2021)
- [Robust Mutual Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.00609/) (2021)
- [All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation](https://mlsanity.com/paper/2305.15832/) (2023)
- [Semi-supervised Semantic Segmentation with Mutual Knowledge Distillation](https://mlsanity.com/paper/2208.11499/) (2022)

## Abstract (arXiv)

Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Self-training methods usually rely on single model prediction confidence to filter low-confidence pseudo labels, thus remaining high-confidence errors and wasting many low-confidence correct labels. In this paper, we point out it is difficult for a model to counter its own errors. Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors. With this new viewpoint, we propose mutual training between two different models by a dynamically re-weighted loss function, called Dynamic Mutual Training (DMT). We quantify inter-model disagreement by comparing predictions from two different models to dynamically re-weight loss in training, where a larger disagreement indicates a possible error and corresponds to a lower loss value. Extensive experiments show that DMT achieves state-of-the-art performance in both image classification and semantic segmentation. Our codes are released at https://github.com/voldemortX/DST-CBC .