# Self-Training for Class-Incremental Semantic Segmentation

arXiv: https://arxiv.org/abs/2012.03362 · HTML: https://mlsanity.com/paper/2012.03362/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2020.

## Built on by (most cited first, 30 of 32)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Federated Incremental Semantic Segmentation](https://mlsanity.com/paper/2304.04620/) (2023)
- [RBC: Rectifying the Biased Context in Continual Semantic Segmentation](https://mlsanity.com/paper/2203.08404/) (2022)
- [SATS: Self-Attention Transfer for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.07667/) (2022)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2210.07207/) (2022)
- [A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application](https://mlsanity.com/paper/2310.14277/) (2023)
- [Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation](https://mlsanity.com/paper/2106.15287/) (2021)
- [InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation](https://mlsanity.com/paper/2302.09886/) (2023)
- [Gradient-Semantic Compensation for Incremental Semantic Segmentation](https://mlsanity.com/paper/2307.10822/) (2023)
- [Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI](https://mlsanity.com/paper/2305.19404/) (2023)
- [Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning](https://mlsanity.com/paper/2312.12722/) (2023)
- [Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning](https://mlsanity.com/paper/2212.08251/) (2022)
- [Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation](https://mlsanity.com/paper/2407.09047/) (2024)
- [Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning](https://mlsanity.com/paper/2408.01076/) (2024)
- [Balanced Residual Distillation Learning for 3D Point Cloud Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2408.01356/) (2024)
- [Self-Improving Semantic Perception for Indoor Localisation](https://mlsanity.com/paper/2105.01595/) (2021)
- [CLEO: Continual Learning of Evolving Ontologies](https://mlsanity.com/paper/2407.08411/) (2024)
- [SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding](https://mlsanity.com/paper/2206.10670/) (2022)
- [Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2209.08010/) (2022)
- [Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions](https://mlsanity.com/paper/2303.14115/) (2023)
- [Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning](https://mlsanity.com/paper/2303.15888/) (2023)
- [ScrollNet: Dynamic Weight Importance for Continual Learning](https://mlsanity.com/paper/2308.16567/) (2023)
- [RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation](https://mlsanity.com/paper/2309.10479/) (2023)
- [Edge-guided and Class-balanced Active Learning for Semantic Segmentation of Aerial Images](https://mlsanity.com/paper/2405.18078/) (2024)
- [Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer](https://mlsanity.com/paper/2502.20124/) (2025)
- [Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning](https://mlsanity.com/paper/2503.00515/) (2025)
- [Smaller Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning](https://mlsanity.com/paper/2105.14106/) (2021)

## Abstract (arXiv)

In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for the rehearsal of previous knowledge. Specifically, we first learn a temporary model for the current task, and then pseudo labels for the unlabeled data are computed by fusing information from the old model of the previous task and the current temporary model. Additionally, conflict reduction is proposed to resolve the conflicts of pseudo labels generated from both the old and temporary models. We show that maximizing self-entropy can further improve results by smoothing the overconfident predictions. Interestingly, in the experiments we show that the auxiliary data can be different from the training data and that even general-purpose but diverse auxiliary data can lead to large performance gains. The experiments demonstrate state-of-the-art results: obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art methods.