Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.10214 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908318166941696 |
|---|---|
| author | Li, Songze Xu, Qixing Su, Tonghua Zhang, Xu-Yao Wang, Zhongjie |
| author_facet | Li, Songze Xu, Qixing Su, Tonghua Zhang, Xu-Yao Wang, Zhongjie |
| contents | The balance between stability and plasticity remains a fundamental challenge in pretrained model-based incremental object detection (PTMIOD). While existing PTMIOD methods demonstrate strong performance on in-domain tasks aligned with pretraining data, their plasticity to cross-domain scenarios remains underexplored. Through systematic component-wise analysis of pretrained detectors, we reveal a fundamental discrepancy: the localization modules demonstrate inherent cross-domain stability-preserving precise bounding box estimation across distribution shifts-while the classification components require enhanced plasticity to mitigate discriminability degradation in cross-domain scenarios. Motivated by these findings, we propose a dual-path framework built upon pretrained DETR-based detectors which decouples localization stability and classification plasticity: the localization path maintains stability to preserve pretrained localization knowledge, while the classification path facilitates plasticity via parameter-efficient fine-tuning and resists forgetting with pseudo-feature replay. Extensive evaluations on both in-domain (MS COCO and PASCAL VOC) and cross-domain (TT100K) benchmarks show state-of-the-art performance, demonstrating our method's ability to effectively balance stability and plasticity in PTMIOD, achieving robust cross-domain adaptation and strong retention of anti-forgetting capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10214 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Balancing Stability and Plasticity in Pretrained Detector: A Dual-Path Framework for Incremental Object Detection Li, Songze Xu, Qixing Su, Tonghua Zhang, Xu-Yao Wang, Zhongjie Computer Vision and Pattern Recognition The balance between stability and plasticity remains a fundamental challenge in pretrained model-based incremental object detection (PTMIOD). While existing PTMIOD methods demonstrate strong performance on in-domain tasks aligned with pretraining data, their plasticity to cross-domain scenarios remains underexplored. Through systematic component-wise analysis of pretrained detectors, we reveal a fundamental discrepancy: the localization modules demonstrate inherent cross-domain stability-preserving precise bounding box estimation across distribution shifts-while the classification components require enhanced plasticity to mitigate discriminability degradation in cross-domain scenarios. Motivated by these findings, we propose a dual-path framework built upon pretrained DETR-based detectors which decouples localization stability and classification plasticity: the localization path maintains stability to preserve pretrained localization knowledge, while the classification path facilitates plasticity via parameter-efficient fine-tuning and resists forgetting with pseudo-feature replay. Extensive evaluations on both in-domain (MS COCO and PASCAL VOC) and cross-domain (TT100K) benchmarks show state-of-the-art performance, demonstrating our method's ability to effectively balance stability and plasticity in PTMIOD, achieving robust cross-domain adaptation and strong retention of anti-forgetting capabilities. |
| title | Balancing Stability and Plasticity in Pretrained Detector: A Dual-Path Framework for Incremental Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10214 |