# Efficient Parameter Mining and Freezing for Continual Object Detection

arXiv: https://arxiv.org/abs/2402.12624 · HTML: https://mlsanity.com/paper/2402.12624/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 14 of 14)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [Wide Neural Networks Forget Less Catastrophically](https://mlsanity.com/paper/2110.11526/) (2021)
- [Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks](https://mlsanity.com/paper/2105.12374/) (2021)
- [Recent Advances in Deep Learning for Object Detection](https://mlsanity.com/paper/1908.03673/) (2019)
- [An Entropy-based Pruning Method for CNN Compression](https://mlsanity.com/paper/1706.05791/) (2017)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)

## Abstract (arXiv)

Continual Object Detection is essential for enabling intelligent agents to interact proactively with humans in real-world settings. While parameter-isolation strategies have been extensively explored in the context of continual learning for classification, they have yet to be fully harnessed for incremental object detection scenarios. Drawing inspiration from prior research that focused on mining individual neuron responses and integrating insights from recent developments in neural pruning, we proposed efficient ways to identify which layers are the most important for a network to maintain the performance of a detector across sequential updates. The presented findings highlight the substantial advantages of layer-level parameter isolation in facilitating incremental learning within object detection models, offering promising avenues for future research and application in real-world scenarios.