DeepAI AI Chat
Log In Sign Up

CBNetV2: A Composite Backbone Network Architecture for Object Detection

by   Tingting Liang, et al.
Ant Financial
Stony Brook University
Alibaba Group
Peking University

Consistent performance gains through exploring more effective network structures. In this paper, we propose a novel backbone network, namely CBNetV2, by constructing compositions of existing open-sourced pre-trained backbones. In particular, CBNetV2 architecture groups multiple identical backbones, which are connected through composite connections. Specifically, CBNetV2 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 the Assistant Supervision for CBNet-based detectors. Without additional pre-training, CBNetV2 can be adapt to various backbones, including manual-based and NAS-based, as well as CNN-based and Transformer-based ones. Experiments provide strong evidence showing that composite backbones are more efficient, effective, and resource-friendly than wider and deeper networks. CBNetV2 is compatible with most mainstream detectors, including one-stage and two-stage detectors, as well as anchor-based and anchor-free-based ones, and significantly improve their performance by more than 3.0 single-scale testing, our HTC Dual-Swin-B achieves 58.6 AP on COCO test-dev, which is significantly better than the state-of-the-art result (i.e., 57.7 Code is released at


CBNet: A Novel Composite Backbone Network Architecture for Object Detection

In existing CNN based detectors, the backbone network is a very importan...

Efficient Decoder-free Object Detection with Transformers

Vision transformers (ViTs) are changing the landscape of object detectio...

MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection

Modern object detection methods can be divided into one-stage approaches...

DetNet: A Backbone network for Object Detection

Recent CNN based object detectors, no matter one-stage methods like YOLO...

You Should Look at All Objects

Feature pyramid network (FPN) is one of the key components for object de...

FQDet: Fast-converging Query-based Detector

Recently, two-stage Deformable DETR introduced the query-based two-stage...

Revisiting Feature Alignment for One-stage Object Detection

Recently, one-stage object detectors gain much attention due to their si...