# Watch Your Step: Optimal Retrieval for Continual Learning at Scale

arXiv: https://arxiv.org/abs/2404.10758 · HTML: https://mlsanity.com/paper/2404.10758/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 16 Apr 2024.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)
- [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)
- [Patching open-vocabulary models by interpolating weights](https://mlsanity.com/paper/2208.05592/) (2022)
- [Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics](https://mlsanity.com/paper/2007.07400/) (2020)
- [Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms](https://mlsanity.com/paper/1908.08619/) (2019)
- [Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning](https://mlsanity.com/paper/2103.13885/) (2021)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning](https://mlsanity.com/paper/2111.11210/) (2021)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [Rehearsal revealed: The limits and merits of revisiting samples in continual learning](https://mlsanity.com/paper/2104.07446/) (2021)
- [A Closer Look at Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2203.17269/) (2022)
- [A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning](https://mlsanity.com/paper/2210.04428/) (2022)
- [First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning](https://mlsanity.com/paper/2303.13199/) (2023)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning](https://mlsanity.com/paper/2302.11344/) (2023)
- [Do Pre-trained Models Benefit Equally in Continual Learning?](https://mlsanity.com/paper/2210.15701/) (2022)
- [GRASP: A Rehearsal Policy for Efficient Online Continual Learning](https://mlsanity.com/paper/2308.13646/) (2023)
- [Memory Population in Continual Learning via Outlier Elimination](https://mlsanity.com/paper/2207.01145/) (2022)
- [Continual Feature Selection: Spurious Features in Continual Learning](https://mlsanity.com/paper/2203.01012/) (2022)

## Built on by (most cited first, 2 of 2)

- [Scalable Strategies for Continual Learning with Replay](https://mlsanity.com/paper/2505.12512/) (2025)
- [Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence](https://mlsanity.com/paper/2609.25735/) (2026)

## Abstract (arXiv)

In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. Replay methods support interleaved learning by storing past experiences in a replay buffer. Although there are methods for selectively constructing the buffer and reprocessing its contents, there is limited exploration of the problem of selectively retrieving samples from the buffer. Current solutions have been tested in limited settings and, more importantly, in isolation. Existing work has also not explored the impact of duplicate replays on performance. In this work, we propose a framework for evaluating selective retrieval strategies, categorized by simple, independent class- and sample-selective primitives. We evaluated several combinations of existing strategies for selective retrieval and present their performances. Furthermore, we propose a set of strategies to prevent duplicate replays and explore whether new samples with low loss values can be learned without replay. In an effort to match our problem setting to a realistic continual learning pipeline, we restrict our experiments to a setting involving a large, pre-trained, open vocabulary object detection model, which is fully fine-tuned on a sequence of 15 datasets.