mlsanityData to 7 Oct 2026

Representation Compensation Networks for Continual Semantic Segmentation

arXiv 2203.05402 ↗First posted 10 Mar 2022cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and stability of the model. We conduct experiments on two challenging continual semantic segmentation scenarios, continual class segmentation and continual domain segmentation. Without any extra computational overhead and parameters during inference, our method outperforms state-of-the-art performance. The code is available at urlhttps://github.com/zhangchbin/RCIL.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). Builds on 88 of its 113 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

88 of 113 references.

References · 88

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  11. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  12. 2016Learning without Forgettingcited by 2,465
38 more
  1. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  2. 2017Non-local Neural Networkscited by 2,290
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  6. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  8. 2016Deep Networks with Stochastic Depthcited by 973
  9. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  10. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  11. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  12. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  13. 2019Large Scale Incremental Learningcited by 727
  14. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  15. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  16. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  17. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  18. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  19. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  20. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 281
  21. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  22. 2018Learning without Memorizingcited by 249
  23. 2021Co2L: Contrastive Continual Learningcited by 243
  24. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  25. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  26. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  27. 2019REMIND Your Neural Network to Prevent Catastrophic Forgettingcited by 197
  28. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
  29. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  30. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  31. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  32. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  33. 2020Learning Joint Spatial-Temporal Transformations for Video Inpaintingcited by 162
  34. 2020Using Hindsight to Anchor Past Knowledge in Continual Learningcited by 160
  35. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  36. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  37. 2019Incremental Learning Techniques for Semantic Segmentationcited by 141
  38. 2020Adversarial Continual Learningcited by 140

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 25; 2024: 23; 2025: 14; 2026: 7.

72 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2023Class-Incremental Learning: A Surveycited by 209
  3. 2023Continual Semantic Segmentation with Automatic Memory Sample Selectioncited by 39
  4. 2023Federated Incremental Semantic Segmentationcited by 36
  5. 2023Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detectioncited by 32
  6. 2022Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentationcited by 28
  7. 2023SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformerscited by 24
  8. 2024Generative Multi-modal Models are Good Class-Incremental Learnerscited by 22
  9. 2022Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentationcited by 21
  10. 2023Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scanscited by 21
  11. 2023A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Applicationcited by 21
  12. 2023Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replaycited by 20
38 more
  1. 2024ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuningcited by 20
  2. 2023Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learningcited by 18
  3. 2023CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentationcited by 18
  4. 2023Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environmentscited by 16
  5. 2024Zero-shot Generalizable Incremental Learning for Vision-Language Object Detectioncited by 15
  6. 2025Rethinking Query-based Transformer for Continual Image Segmentationcited by 14
  7. 2023Overcoming the Stability Gap in Continual Learningcited by 13
  8. 2023FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understandingcited by 13
  9. 2023Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memorycited by 12
  10. 2023Continual Learning for Image Segmentation with Dynamic Querycited by 12
  11. 2023Gradient-Semantic Compensation for Incremental Semantic Segmentationcited by 10
  12. 2024Strike a Balance in Continual Panoptic Segmentationcited by 10
  13. 2022Learning with Style: Continual Semantic Segmentation Across Tasks and Domainscited by 9
  14. 2023Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRIcited by 9
  15. 2023Self-paced Weight Consolidation for Continual Learningcited by 9
  16. 2024Continual Segmentation with Disentangled Objectness Learning and Class Recognitioncited by 8
  17. 2024Mitigating Background Shift in Class-Incremental Semantic Segmentationcited by 8
  18. 2024Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perceptioncited by 8
  19. 2023MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognitioncited by 7
  20. 2024Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentationcited by 7
  21. 2024Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentationcited by 7
  22. 2024Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modellingcited by 6
  23. 2024Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentationcited by 6
  24. 2025Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentationcited by 6
  25. 2025CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentationcited by 6
  26. 2024CLEO: Continual Learning of Evolving Ontologiescited by 5
  27. 2024Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentationcited by 5
  28. 2024Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentationcited by 5
  29. 2023RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentationcited by 4
  30. 2024Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learningcited by 4
  31. 2024Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Imagescited by 4
  32. 2024ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformercited by 3
  33. 2025Dynamic Robot-Assisted Surgery with Hierarchical Class-Incremental Semantic Segmentationcited by 3
  34. 2023Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Modelcited by 2
  35. 2024BACS: Background Aware Continual Semantic Segmentationcited by 2
  36. 2024AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentationcited by 2
  37. 2024CFSSeg: Closed-Form Solution for Class-Incremental Semantic Segmentation of 2D Images and 3D Point Cloudscited by 2
  38. 2025CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptationcited by 2

50 most cited of 72 All 72 (JSON)