# Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos

arXiv: https://arxiv.org/abs/2310.16115 · HTML: https://mlsanity.com/paper/2310.16115/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 30 of 34)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Semantic Drift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2004.00440/) (2020)
- [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://mlsanity.com/paper/2204.04662/) (2022)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Reinforced Continual Learning](https://mlsanity.com/paper/1805.12369/) (2018)
- [Class-incremental Learning via Deep Model Consolidation](https://mlsanity.com/paper/1903.07864/) (2019)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Adaptive Aggregation Networks for Class-Incremental Learning](https://mlsanity.com/paper/2010.05063/) (2020)
- [Conditional Channel Gated Networks for Task-Aware Continual Learning](https://mlsanity.com/paper/2004.00070/) (2020)
- [Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation](https://mlsanity.com/paper/2204.00895/) (2022)
- [Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild](https://mlsanity.com/paper/1903.12648/) (2019)
- [On Learning the Geodesic Path for Incremental Learning](https://mlsanity.com/paper/2104.08572/) (2021)
- [RMM: Reinforced Memory Management for Class-Incremental Learning](https://mlsanity.com/paper/2301.05792/) (2023)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [Class-Incremental Exemplar Compression for Class-Incremental Learning](https://mlsanity.com/paper/2303.14042/) (2023)
- [Continual Learning for Abdominal Multi-Organ and Tumor Segmentation](https://mlsanity.com/paper/2306.00988/) (2023)
- [Energy-based Latent Aligner for Incremental Learning](https://mlsanity.com/paper/2203.14952/) (2022)
- [Online Hyperparameter Optimization for Class-Incremental Learning](https://mlsanity.com/paper/2301.05032/) (2023)

## Built on by (most cited first, 14 of 14)

- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning](https://mlsanity.com/paper/2410.00911/) (2024)
- [How to Teach Large Multimodal Models New Skills](https://mlsanity.com/paper/2510.08564/) (2025)
- [iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning](https://mlsanity.com/paper/2407.09271/) (2024)
- [Continual Adversarial Defense](https://mlsanity.com/paper/2312.09481/) (2023)
- [Future-Proofing Class-Incremental Learning](https://mlsanity.com/paper/2404.03200/) (2024)
- [Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning](https://mlsanity.com/paper/2311.18266/) (2023)
- [Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction](https://mlsanity.com/paper/2603.06852/) (2026)
- [AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation](https://mlsanity.com/paper/2606.31204/) (2026)
- [RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2610.01969/) (2026)
- [Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning](https://mlsanity.com/paper/2603.01759/) (2026)
- [AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning](https://mlsanity.com/paper/2607.15094/) (2026)
- [Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference](https://mlsanity.com/paper/2610.01989/) (2026)
- [4Director: Controlling Video World Models with Rigid 3D Geometry](https://mlsanity.com/paper/2610.02160/) (2026)

## Abstract (arXiv)

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction inconsistencies between old and new models. Such prediction is made with almost new class data, as old class data is extremely scarce due to the strict memory limitation in CIL. In this paper, we take a deep dive into KD losses and find that "using new class data for KD" not only hinders the model adaption (for learning new classes) but also results in low efficiency for preserving old class knowledge. We address this by "using the placebos of old classes for KD", where the placebos are chosen from a free image stream, such as Google Images, in an automatical and economical fashion. To this end, we train an online placebo selection policy to quickly evaluate the quality of streaming images (good or bad placebos) and use only good ones for one-time feed-forward computation of KD. We formulate the policy training process as an online Markov Decision Process (MDP), and introduce an online learning algorithm to solve this MDP problem without causing much computation costs. In experiments, we show that our method 1) is surprisingly effective even when there is no class overlap between placebos and original old class data, 2) does not require any additional supervision or memory budget, and 3) significantly outperforms a number of top-performing CIL methods, in particular when using lower memory budgets for old class exemplars, e.g., five exemplars per class.