# Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation

arXiv: https://arxiv.org/abs/2106.15287 · HTML: https://mlsanity.com/paper/2106.15287/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 83 of its 111 references that are in the map.
- First posted on arXiv 29 Jun 2021.

## Builds on (most cited first, 30 of 83)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)

## Built on by (most cited first, 15 of 15)

- [DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion](https://mlsanity.com/paper/2111.11326/) (2021)
- [SATS: Self-Attention Transfer for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.07667/) (2022)
- [CoMFormer: Continual Learning in Semantic and Panoptic Segmentation](https://mlsanity.com/paper/2211.13999/) (2022)
- [Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2210.07207/) (2022)
- [TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation](https://mlsanity.com/paper/2202.13393/) (2022)
- [Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2204.11667/) (2022)
- [Subspace Distillation for Continual Learning](https://mlsanity.com/paper/2307.16419/) (2023)
- [Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection](https://mlsanity.com/paper/2209.09839/) (2022)
- [Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark](https://mlsanity.com/paper/2404.06859/) (2024)
- [Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation](https://mlsanity.com/paper/2503.22136/) (2025)
- [CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation](https://mlsanity.com/paper/2504.04156/) (2025)
- [Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2209.08010/) (2022)
- [Effects of Architectures on Continual Semantic Segmentation](https://mlsanity.com/paper/2302.10718/) (2023)
- [BACS: Background Aware Continual Semantic Segmentation](https://mlsanity.com/paper/2404.13148/) (2024)
- [Delving into Transformer for Incremental Semantic Segmentation](https://mlsanity.com/paper/2211.10253/) (2022)

## Abstract (arXiv)

Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale pooling distillation scheme that preserves long- and short-range spatial relationships at feature level. Furthermore, we design an entropy-based pseudo-labelling of the background w.r.t. classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes. Finally, we introduce a novel rehearsal method that is particularly suited for segmentation. Our approach, called PLOP, significantly outperforms state-of-the-art methods in existing CSS scenarios, as well as in newly proposed challenging benchmarks.