# Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks

arXiv: https://arxiv.org/abs/2503.07107 · HTML: https://mlsanity.com/paper/2503.07107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 90 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [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)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions](https://mlsanity.com/paper/2003.03488/) (2020)
- [Memory-Efficient Incremental Learning Through Feature Adaptation](https://mlsanity.com/paper/2004.00713/) (2020)
- [A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks](https://mlsanity.com/paper/2011.01844/) (2020)
- [Latent Replay for Real-Time Continual Learning](https://mlsanity.com/paper/1912.01100/) (2019)
- [Rethinking Experience Replay: a Bag of Tricks for Continual Learning](https://mlsanity.com/paper/2010.05595/) (2020)

## Abstract (arXiv)

Binary Neural Networks (BNNs) are a promising approach to enable Artificial Neural Network (ANN) implementation on ultra-low power edge devices. Such devices may compute data in highly dynamic environments, in which the classes targeted for inference can evolve or even novel classes may arise, requiring continual learning. Class Incremental Learning (CIL) is a common type of continual learning for classification problems, that has been scarcely addressed in the context of BNNs. Furthermore, most of existing BNNs models are not fully binary, as they require several real-valued network layers, at the input, the output, and for batch normalization. This paper goes a step further, enabling class incremental learning in Fully-Binarized NNs (FBNNs) through four main contributions. We firstly revisit the FBNN design and its training procedure that is suitable to CIL. Secondly, we explore loss balancing, a method to trade-off the performance of past and current classes. Thirdly, we propose a semi-supervised method to pre-train the feature extractor of the FBNN for transferable representations. Fourthly, two conventional CIL methods, ie, Latent and Native replay, are thoroughly compared. These contributions are exemplified first on the CIFAR100 dataset, before being scaled up to address the CORE50 continual learning benchmark. The final results based on our 3Mb FBNN on CORE50 exhibit at par and better performance than conventional real-valued larger NN models.