# CBNet: A Novel Composite Backbone Network Architecture for Object Detection

arXiv: https://arxiv.org/abs/1909.03625 · HTML: https://mlsanity.com/paper/1909.03625/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 30 of 44)

- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Lite Vision Transformer with Enhanced Self-Attention](https://mlsanity.com/paper/2112.10809/) (2021)
- [CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation](https://mlsanity.com/paper/2206.08948/) (2022)
- [BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training](https://mlsanity.com/paper/2203.13249/) (2022)
- [PP-YOLOv2: A Practical Object Detector](https://mlsanity.com/paper/2104.10419/) (2021)
- [Robust Table Detection and Structure Recognition from Heterogeneous Document Images](https://mlsanity.com/paper/2203.09056/) (2022)
- [Sliced Recursive Transformer](https://mlsanity.com/paper/2111.05297/) (2021)
- [Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation](https://mlsanity.com/paper/2105.12971/) (2021)
- [A Survey and Framework of Cooperative Perception: From Heterogeneous Singleton to Hierarchical Cooperation](https://mlsanity.com/paper/2208.10590/) (2022)
- [Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks](https://mlsanity.com/paper/2104.14272/) (2021)
- [DynamicDet: A Unified Dynamic Architecture for Object Detection](https://mlsanity.com/paper/2304.05552/) (2023)
- [Infrastructure-Based Object Detection and Tracking for Cooperative Driving Automation: A Survey](https://mlsanity.com/paper/2201.11871/) (2022)
- [Unsupervised Multi-object Segmentation Using Attention and Soft-argmax](https://mlsanity.com/paper/2205.13271/) (2022)
- [RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2309.00655/) (2023)
- [CE-FPN: Enhancing Channel Information for Object Detection](https://mlsanity.com/paper/2103.10643/) (2021)
- [Nuclei Grading of Clear Cell Renal Cell Carcinoma in Histopathological Image by Composite High-Resolution Network](https://mlsanity.com/paper/2106.10641/) (2021)
- [Geometric-aware Pretraining for Vision-centric 3D Object Detection](https://mlsanity.com/paper/2304.03105/) (2023)
- [Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer](https://mlsanity.com/paper/2305.02769/) (2023)
- [Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance](https://mlsanity.com/paper/2104.03888/) (2021)
- [EZCrop: Energy-Zoned Channels for Robust Output Pruning](https://mlsanity.com/paper/2105.03679/) (2021)
- [MSN: Efficient Online Mask Selection Network for Video Instance Segmentation](https://mlsanity.com/paper/2106.10452/) (2021)
- [PECAN: A Product-Quantized Content Addressable Memory Network](https://mlsanity.com/paper/2208.13571/) (2022)
- [Tracking one-in-a-million: Large-scale benchmark for microbial single-cell tracking with experiment-aware robustness metrics](https://mlsanity.com/paper/2411.00552/) (2024)
- [ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne Detection](https://mlsanity.com/paper/2105.14891/) (2021)
- [Universal Object Detection with Large Vision Model](https://mlsanity.com/paper/2212.09408/) (2022)
- [Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer](https://mlsanity.com/paper/2405.00187/) (2024)
- [Embedded Feature Similarity Optimization with Specific Parameter Initialization for 2D/3D Medical Image Registration](https://mlsanity.com/paper/2305.06252/) (2023)

## Abstract (arXiv)

In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by building a more powerful backbone from existing backbones like ResNet and ResNeXt. Specifically, we propose a novel strategy for assembling multiple identical backbones by composite connections between the adjacent backbones, to form a more powerful backbone named Composite Backbone Network (CBNet). In this way, CBNet iteratively feeds the output features of the previous backbone, namely high-level features, as part of input features to the succeeding backbone, in a stage-by-stage fashion, and finally the feature maps of the last backbone (named Lead Backbone) are used for object detection. We show that CBNet can be very easily integrated into most state-of-the-art detectors and significantly improve their performances. For example, it boosts the mAP of FPN, Mask R-CNN and Cascade R-CNN on the COCO dataset by about 1.5 to 3.0 percent. Meanwhile, experimental results show that the instance segmentation results can also be improved. Specially, by simply integrating the proposed CBNet into the baseline detector Cascade Mask R-CNN, we achieve a new state-of-the-art result on COCO dataset (mAP of 53.3) with single model, which demonstrates great effectiveness of the proposed CBNet architecture. Code will be made available on https://github.com/PKUbahuangliuhe/CBNet.