# CRAM: Large-scale Video Continual Learning with Bootstrapped Compression

arXiv: https://arxiv.org/abs/2508.05001 · HTML: https://mlsanity.com/paper/2508.05001/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 58 references that are in the map.
- First posted on arXiv 7 Aug 2025.

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

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [Self-supervised Co-training for Video Representation Learning](https://mlsanity.com/paper/2010.09709/) (2020)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [REMIND Your Neural Network to Prevent Catastrophic Forgetting](https://mlsanity.com/paper/1910.02509/) (2019)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [MGSampler: An Explainable Sampling Strategy for Video Action Recognition](https://mlsanity.com/paper/2104.09952/) (2021)
- [EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding](https://mlsanity.com/paper/2309.08816/) (2023)
- [CLAD: A realistic Continual Learning benchmark for Autonomous Driving](https://mlsanity.com/paper/2210.03482/) (2022)
- [Wanderlust: Online Continual Object Detection in the Real World](https://mlsanity.com/paper/2108.11005/) (2021)
- [vCLIMB: A Novel Video Class Incremental Learning Benchmark](https://mlsanity.com/paper/2201.09381/) (2022)
- [The Overfitted Brain: Dreams evolved to assist generalization](https://mlsanity.com/paper/2007.09560/) (2020)
- [Label-Efficient Online Continual Object Detection in Streaming Video](https://mlsanity.com/paper/2206.00309/) (2022)
- [TIM: A Time Interval Machine for Audio-Visual Action Recognition](https://mlsanity.com/paper/2404.05559/) (2024)
- [Turbo Training with Token Dropout](https://mlsanity.com/paper/2210.04889/) (2022)
- [Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning](https://mlsanity.com/paper/2211.00833/) (2022)
- [Just a Glimpse: Rethinking Temporal Information for Video Continual Learning](https://mlsanity.com/paper/2305.18418/) (2023)
- [Compressed Vision for Efficient Video Understanding](https://mlsanity.com/paper/2210.02995/) (2022)

## Built on by (most cited first, 1 of 1)

- [I Have a Stream: Making Self-Supervised Learning Work on Continuous Video](https://mlsanity.com/paper/2609.40333/) (2026)

## Abstract (arXiv)

Continual learning (CL) promises to allow neural networks to learn from continuous streams of inputs, instead of IID (independent and identically distributed) sampling, which requires random access to a full dataset. This would allow for much smaller storage requirements and self-sufficiency of deployed systems that cope with natural distribution shifts, similarly to biological learning. We focus on video CL employing a rehearsal-based approach, which reinforces past samples from a memory buffer. We posit that part of the reason why practical video CL is challenging is the high memory requirements of video, further exacerbated by long-videos and continual streams, which are at odds with the common rehearsal-buffer size constraints. To address this, we propose to use compressed vision, i.e. store video codes (embeddings) instead of raw inputs, and train a video classifier by IID sampling from this rolling buffer. Training a video compressor online (so not depending on any pre-trained networks) means that it is also subject to catastrophic forgetting. We propose a scheme to deal with this forgetting by refreshing video codes, which requires careful decompression with a previous version of the network and recompression with a new one. We name our method Continually Refreshed Amodal Memory (CRAM). We expand current video CL benchmarks to large-scale settings, namely EpicKitchens-100 and Kinetics-700, storing thousands of relatively long videos in under 2 GB, and demonstrate empirically that our video CL method outperforms prior art with a significantly reduced memory footprint.