English

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

Computer Vision and Pattern Recognition 2023-08-15 v2 Artificial Intelligence Machine Learning

Abstract

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limit the detector's performance, generalization ability, and convergence speed. To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies. AlignDet decouples the pre-training process into two stages, i.e., image-domain and box-domain pre-training. The image-domain pre-training optimizes the detection backbone to capture holistic visual abstraction, and box-domain pre-training learns instance-level semantics and task-aware concepts to initialize the parts out of the backbone. By incorporating the self-supervised pre-trained backbones, we can pre-train all modules for various detectors in an unsupervised paradigm. As depicted in Figure 1, extensive experiments demonstrate that AlignDet can achieve significant improvements across diverse protocols, such as detection algorithm, model backbone, data setting, and training schedule. For example, AlignDet improves FCOS by 5.3 mAP, RetinaNet by 2.1 mAP, Faster R-CNN by 3.3 mAP, and DETR by 2.3 mAP under fewer epochs.

Keywords

Cite

@article{arxiv.2307.11077,
  title  = {AlignDet: Aligning Pre-training and Fine-tuning in Object Detection},
  author = {Ming Li and Jie Wu and Xionghui Wang and Chen Chen and Jie Qin and Xuefeng Xiao and Rui Wang and Min Zheng and Xin Pan},
  journal= {arXiv preprint arXiv:2307.11077},
  year   = {2023}
}

Comments

Camera Ready Version on ICCV 2023. Code and Models are publicly available. Project Page: https://liming-ai.github.io/AlignDet

R2 v1 2026-06-28T11:36:14.118Z