GiraffeDet: A Heavy-Neck Paradigm for Object Detection

by   Yiqi Jiang, et al.

In conventional object detection frameworks, a backbone body inherited from image recognition models extracts deep latent features and then a neck module fuses these latent features to capture information at different scales. As the resolution in object detection is much larger than in image recognition, the computational cost of the backbone often dominates the total inference cost. This heavy-backbone design paradigm is mostly due to the historical legacy when transferring image recognition models to object detection rather than an end-to-end optimized design for object detection. In this work, we show that such paradigm indeed leads to sub-optimal object detection models. To this end, we propose a novel heavy-neck paradigm, GiraffeDet, a giraffe-like network for efficient object detection. The GiraffeDet uses an extremely lightweight backbone and a very deep and large neck module which encourages dense information exchange among different spatial scales as well as different levels of latent semantics simultaneously. This design paradigm allows detectors to process the high-level semantic information and low-level spatial information at the same priority even in the early stage of the network, making it more effective in detection tasks. Numerical evaluations on multiple popular object detection benchmarks show that GiraffeDet consistently outperforms previous SOTA models across a wide spectrum of resource constraints.


ThunderNet: Towards Real-time Generic Object Detection

Real-time generic object detection on mobile platforms is a crucial but ...

Decoupled Self Attention for Accurate One Stage Object Detection

As the scale of object detection dataset is smaller than that of image r...

DetNet: A Backbone network for Object Detection

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

SparseDet: Towards End-to-End 3D Object Detection

In this paper, we propose SparseDet for end-to-end 3D object detection f...

Proper Reuse of Image Classification Features Improves Object Detection

A common practice in transfer learning is to initialize the downstream m...

Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

Object detection has made great progress in the past few years along wit...

Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks

In Convolutional Neural Network (CNN) based image processing, most of th...

Please sign up or login with your details

Forgot password? Click here to reset