CBNet:一种用于目标检测的复合骨干网络结构
CBNet: A Composite Backbone Network Architecture for Object Detection
摘要:
现代高性能的目标检测器严重依赖于骨干网络,骨干网络的进步通过探索更有效的网络结构带来了一致的性能增益。在本文中,我们提出了一种新颖而灵活的骨干框架,即CBNetV 2,在预训练微调范式下使用现有的开源预训练骨干来构建高性能检测器。特别是,CBNetV 2架构将多个相同的骨干网分组,这些骨干网通过复合连接进行连接。具体而言,它集成了多个骨干网络的高级和低级特征,并逐渐扩大了感受野,以更有效地执行目标检测。我们还提出了一个更好的训练策略与基于CBNet的检测器的辅助监督。无需对复合主干进行额外的预训练,CBNetV 2可以适应大多数主流检测器的各种主干(基于CNN与基于Transformer)和头部设计(单级与两级,基于锚与无锚)。实验提供了强有力的证据,与简单地增加网络的深度和宽度相比,CBNetV 2引入了一种更高效,有效和资源友好的方式来构建高性能的骨干网络。特别地,我们的Dual-Swin-L在单模型和单尺度测试协议下在COCO test-dev上实现了59.4%的box AP和51.6%的mask AP,这显著优于Swin-L实现的最先进的结果(57.7%的box AP和50.2%的mask AP),而训练时间表减少了6个$\times$。通过多尺度测试,我们在不使用额外训练数据的情况下,将当前最好的单个模型结果推到60.1%的箱AP和52.3%的掩模AP的新记录。代码可在https://github.com/VDIGPKU/CBNetV2上获得。
英文摘要:
Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone framework, namely CBNetV2, to construct high-performance detectors using existing open-sourced pre-trained backbones under the pre-training fine-tuning paradigm. In particular, CBNetV2 architecture groups multiple identical backbones, which are connected through composite connections. Specifically, it integrates the high- and low-level features of multiple backbone networks and gradually expands the receptive field to more efficiently perform object detection. We also propose a better training strategy with assistant supervision for CBNet-based detectors. Without additional pre-training of the composite backbone, CBNetV2 can be adapted to various backbones (CNN-based vs. Transformer-based) and head designs of most mainstream detectors (one-stage vs. two-stage, anchor-based vs. anchor-free-based). Experiments provide strong evidence that, compared with simply increasing the depth and width of the network, CBNetV2 introduces a more efficient, effective, and resource-friendly way to build high-performance backbone networks. Particularly, our Dual-Swin-L achieves 59.4% box AP and 51.6% mask AP on COCO test-dev under the single-model and single-scale testing protocol, which is significantly better than the state-of-the-art result (57.7% box AP and 50.2% mask AP) achieved by Swin-L, while the training schedule is reduced by 6$\times$. With multi-scale testing, we push the current best single model result to a new record of 60.1% box AP and 52.3% mask AP without using extra training data. Code is available at https://github.com/VDIGPKU/CBNetV2.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。