# Fine-Tuning Without Forgetting: Adaptation of YOLOv8 Preserves COCO Performance

arXiv: https://arxiv.org/abs/2505.01016 · HTML: https://mlsanity.com/paper/2505.01016/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 2 May 2025.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [What makes ImageNet good for transfer learning?](https://mlsanity.com/paper/1608.08614/) (2016)

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

- [An Analysis of Layer-Freezing Strategies for Enhanced Transfer Learning in YOLO Architectures](https://mlsanity.com/paper/2509.05490/) (2025)

## Abstract (arXiv)

The success of large pre-trained object detectors hinges on their adaptability to diverse downstream tasks. While fine-tuning is the standard adaptation method, specializing these models for challenging fine-grained domains necessitates careful consideration of feature granularity. The critical question remains: how deeply should the pre-trained backbone be fine-tuned to optimize for the specialized task without incurring catastrophic forgetting of the original general capabilities? Addressing this, we present a systematic empirical study evaluating the impact of fine-tuning depth. We adapt a standard YOLOv8n model to a custom, fine-grained fruit detection dataset by progressively unfreezing backbone layers (freeze points at layers 22, 15, and 10) and training. Performance was rigorously evaluated on both the target fruit dataset and, using a dual-head evaluation architecture, on the original COCO validation set. Our results demonstrate unequivocally that deeper fine-tuning (unfreezing down to layer 10) yields substantial performance gains (e.g., +10% absolute mAP50) on the fine-grained fruit task compared to only training the head. Strikingly, this significant adaptation and specialization resulted in negligible performance degradation (<0.1% absolute mAP difference) on the COCO benchmark across all tested freeze levels. We conclude that adapting mid-to-late backbone features is highly effective for fine-grained specialization. Critically, our results demonstrate this adaptation can be achieved without the commonly expected penalty of catastrophic forgetting, presenting a compelling case for exploring deeper fine-tuning strategies, particularly when targeting complex domains or when maximizing specialized performance is paramount.