Generalizable Two-Branch Framework for Image Class-Incremental Learning
Abstract: Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and achieved substantial improvements. In this paper, a novel two-branch continual learning framework is proposed to further enhance most existing CL methods. Specifically, the main branch can be any existing CL model and the newly introduced side branch is a lightweight convolutional network. The output of each main branch block is modulated by the output of the corresponding side branch block. Such a simple two-branch model can then be easily implemented and learned with the vanilla optimization setting without whistles and bells. Extensive experiments with various settings on multiple image datasets show that the proposed framework yields consistent improvements over state-of-the-art methods.
- Robert M French, “Catastrophic forgetting in connectionist networks,” Trends in Cognitive Sciences, 1999.
- “Catastrophic interference in connectionist networks: The sequential learning problem,” Trends in Cognitive Sciences, 1989.
- “Podnet: Pooled outputs distillation for small-tasks incremental learning,” in Proceedings of the IEEE European Conference on Computer Vision (ECCV), 2020.
- “Learning without forgetting,” in Proceedings of the IEEE European Conference on Computer Vision (ECCV), 2016.
- “Overcoming catastrophic forgetting in neural networks,” Proceedings of the National Academy of Sciences, 2016.
- “Large scale incremental learning,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
- “Dark experience for general continual learning: a strong, simple baseline,” in Advances in Neural Information Processing Systems (NeurIPS), 2020.
- “Measuring and regularizing networks in function space,” in Proceedings of the International Conference on Learning Representations (ICLR), 2019.
- “Efficient lifelong learning with A-GEM,” in Proceedings of the International Conference on Learning Representations (ICLR), 2019.
- “icarl: Incremental classifier and representation learning,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
- “Dytox: Transformers for continual learning with dynamic token expansion,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
- “DER: dynamically expandable representation for class incremental learning,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
- “Lifelong learning with dynamically expandable networks,” in Proceedings of the International Conference on Learning Representations (ICLR), 2018.
- “Side-tuning: A baseline for network adaptation via additive side networks,” in Proceedings of the IEEE European Conference on Computer Vision (ECCV), 2020.
- “Lifelong learning with dynamically expandable networks,,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
- “Learning multiple layers of features from tiny images,” Technical Report, 2009.
- “Imagenet: A large-scale hierarchical image database,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.
- “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
- “Riemannian walk for incremental learning: Understanding forgetting and intransigence,” in Proceedings of the IEEE European Conference on Computer Vision (ECCV), 2018.
- “Adaptive aggregation networks for class-incremental learning,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
