CBNet: A Composite Backbone Network Architecture for Object Detection

By Tingting Liang, Xiao Chu, Yudong Liu, Yongtao Wang, Zhi Tang, Wei Chu, Jingdong Chen, Haibin Ling. 2021

224 citations recorded by the source corpus.

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 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-model and single-scale testing protocol, which are significantly better than the state-of-the-art results (i.e., 57.7% box AP and 50.2% mask AP) achieved by Swin-L, while reducing the training time 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Exploring Plain Vision Transformer Backbones for Object Detection (2022, methodology): “†: these entries use CBNetV2 [34] that combines two Swin-L backbones.”
BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework (2022, methodology): “We conduct BEVFusion with CB-Swin-Tiny [25] as 2D bakbone for image-view encoder.”
EVA-02: A Visual Representation for Neon Genesis (2023, methodology): “The baselines we compared also adopt improved settings such as larger input resolution, Soft-NMS, etc ., and RevCol “ †† ”: encoder parameters doubled using model composite technique [77] initializes HTC++ [23, 82] as the task layer, which is an improved version of Cascade Mask R-CNN we used.”
LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation (2021, background): “The learning rate is set to 0.0001 and 0.00005 corresponding to single swin-L backbone and CBNetV2 backbone.”
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (2024, methodology): “CBNet [34, 39] re-introduces the original input data through composite backbone to obtain complete original information, and obtains different levels of multi-level reversible information through various composition methods.”