# Diverse Cotraining Makes Strong Semi-Supervised Segmentor

arXiv: https://arxiv.org/abs/2308.09281 · HTML: https://mlsanity.com/paper/2308.09281/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 100 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Builds on (most cited first, 30 of 78)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)

## Built on by (most cited first, 26 of 26)

- [Diffusion Model as Representation Learner](https://mlsanity.com/paper/2308.10916/) (2023)
- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance](https://mlsanity.com/paper/2311.16241/) (2023)
- [AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.01818/) (2024)
- [On-Policy Self-Distillation without Any Supervision](https://mlsanity.com/paper/2608.06296/) (2026)
- [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)
- [Probing Mechanical Reasoning in Large Vision Language Models](https://mlsanity.com/paper/2410.00318/) (2024)
- [Probing Perceptual Constancy in Large Vision-Language Models](https://mlsanity.com/paper/2502.10273/) (2025)
- [PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2405.20610/) (2024)
- [Self-Supervised Visual On-Policy Distillation](https://mlsanity.com/paper/2608.14144/) (2026)
- [Vision Language Models Know Law of Conservation without Understanding More-or-Less](https://mlsanity.com/paper/2410.00332/) (2024)
- [Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2501.01640/) (2025)
- [Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness](https://mlsanity.com/paper/2506.05917/) (2025)
- [Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learner](https://mlsanity.com/paper/2311.10887/) (2023)
- [Cognitive-Inspired Hierarchical Attention Fusion With Visual and Textual for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2504.15085/) (2025)
- [FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2506.11142/) (2025)
- [Towards Understanding Adversarial Transferability in Federated Learning](https://mlsanity.com/paper/2310.00616/) (2023)
- [S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2407.07763/) (2024)
- [Knowledge Consultation for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2503.10693/) (2025)
- [Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation](https://mlsanity.com/paper/2506.13925/) (2025)
- [Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2411.05307/) (2024)
- [BoundMatch: Boundary detection applied to semi-supervised segmentation](https://mlsanity.com/paper/2503.23519/) (2025)
- [SWDL: Stratum-Wise Difference Learning with Deep Laplacian Pyramid for Semi-Supervised 3D Intracranial Hemorrhage Segmentation](https://mlsanity.com/paper/2506.10325/) (2025)
- [Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model](https://mlsanity.com/paper/2507.03302/) (2025)
- [SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks](https://mlsanity.com/paper/2509.22581/) (2025)

## Abstract (arXiv)

Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, we revisit the core assumption that supports co-training: multiple compatible and conditionally independent views. By theoretically deriving the generalization upper bound, we prove the prediction similarity between two models negatively impacts the model's generalization ability. However, most current co-training models are tightly coupled together and violate this assumption. Such coupling leads to the homogenization of networks and confirmation bias which consequently limits the performance. To this end, we explore different dimensions of co-training and systematically increase the diversity from the aspects of input domains, different augmentations and model architectures to counteract homogenization. Our Diverse Co-training outperforms the state-of-the-art (SOTA) methods by a large margin across different evaluation protocols on the Pascal and Cityscapes. For example. we achieve the best mIoU of 76.2%, 77.7% and 80.2% on Pascal with only 92, 183 and 366 labeled images, surpassing the previous best results by more than 5%.