CBNet: A Composite Backbone Network Architecture for Object Detection

作者：Tingting Liang, Xiaojie Chu, Yudong Liu, Yongtao Wang, Zhi Tang, Wei Chu, Jingdong Chen, Haibin Ling · 发表于：IEEE Transactions on Image Processing · 年份：2022 · DOI：10.1109/tip.2022.3216771 · 被引用次数：175 · 研究领域：Advanced Neural Network Applications、Domain Adaptation and Few-Shot Learning、Adversarial Robustness in Machine Learning

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 CBNet, to construct high-performance detectors using existing open-source pre-trained backbones under the pre-training fine-tuning paradigm. In particular, CBNet architecture groups multiple identical backbones, which are connected through composite connections. Specifically, it integrates the high- and low-level features of multiple identical backbone networks and gradually expands the receptive field to more effectively perform object detection. We also propose a better training strategy with auxiliary supervision for CBNet-based detectors. CBNet has strong generalization capabilities for different backbones and head designs of the detector architecture. Without additional pre-training of the composite backbone, CBNet can be adapted to various backbones (i.e., CNN-based vs. Transformer-based) and head designs of most mainstream detectors (i.e., 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, CBNet introduces a more efficient, effective, and resource-friendly way to build high-performance backbone networks. Particularly, our CB-Swin-L achieves 59.4% box AP and 51.6% mask AP on COCO test-dev under the single-mode...