# Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

arXiv: https://arxiv.org/abs/2106.09701 · HTML: https://mlsanity.com/paper/2106.09701/

## Key facts

- Cited by 131 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 66 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [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)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines](https://mlsanity.com/paper/1810.12488/) (2018)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [FearNet: Brain-Inspired Model for Incremental Learning](https://mlsanity.com/paper/1711.10563/) (2017)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [Data-Free Knowledge Distillation for Deep Neural Networks](https://mlsanity.com/paper/1710.07535/) (2017)
- [A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning](https://mlsanity.com/paper/2001.00689/) (2020)
- [Memory Efficient Experience Replay for Streaming Learning](https://mlsanity.com/paper/1809.05922/) (2018)

## Built on by (most cited first, 30 of 131)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA](https://mlsanity.com/paper/2304.06027/) (2023)
- [A Unified Continual Learning Framework with General Parameter-Efficient Tuning](https://mlsanity.com/paper/2303.10070/) (2023)
- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (2022)
- [Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal](https://mlsanity.com/paper/2403.01244/) (2024)
- [Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2303.06628/) (2023)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Representation Compensation Networks for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.05402/) (2022)
- [Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay](https://mlsanity.com/paper/2207.11213/) (2022)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation](https://mlsanity.com/paper/2303.06937/) (2023)
- [R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning](https://mlsanity.com/paper/2203.13104/) (2022)
- [A Closer Look at Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2203.17269/) (2022)
- [Consistent Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2403.08568/) (2024)
- [Real-Time Evaluation in Online Continual Learning: A New Hope](https://mlsanity.com/paper/2302.01047/) (2023)
- [PIVOT: Prompting for Video Continual Learning](https://mlsanity.com/paper/2212.04842/) (2022)
- [A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks](https://mlsanity.com/paper/2311.07784/) (2023)
- [Divide and not forget: Ensemble of selectively trained experts in Continual Learning](https://mlsanity.com/paper/2401.10191/) (2024)
- [Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning](https://mlsanity.com/paper/2402.03917/) (2024)
- [Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector](https://mlsanity.com/paper/2110.07905/) (2021)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Continual Sequence Generation with Adaptive Compositional Modules](https://mlsanity.com/paper/2203.10652/) (2022)
- [Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation](https://mlsanity.com/paper/2209.10359/) (2022)
- [Class-Incremental Learning using Diffusion Model for Distillation and Replay](https://mlsanity.com/paper/2306.17560/) (2023)

## Abstract (arXiv)

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which is problematic when memory constraints or data legality concerns exist. In this work, we consider the high-impact problem of Data-Free Class-Incremental Learning (DFCIL), where an incremental learning agent must learn new concepts over time without storing generators or training data from past tasks. One approach for DFCIL is to replay synthetic images produced by inverting a frozen copy of the learner's classification model, but we show this approach fails for common class-incremental benchmarks when using standard distillation strategies. We diagnose the cause of this failure and propose a novel incremental distillation strategy for DFCIL, contributing a modified cross-entropy training and importance-weighted feature distillation, and show that our method results in up to a 25.1% increase in final task accuracy (absolute difference) compared to SOTA DFCIL methods for common class-incremental benchmarks. Our method even outperforms several standard replay based methods which store a coreset of images.