GiraffeDet: A Heavy-Neck Paradigm for Object Detection

TL;DR

GiraffeDet introduces a novel heavy-neck paradigm with a lightweight backbone and a deep, dense neck module, enabling more efficient and accurate object detection by processing semantic and spatial information simultaneously.

Contribution

The paper proposes a new heavy-neck paradigm for object detection, replacing the traditional heavy-backbone approach with a lightweight backbone and a deep neck for improved efficiency and performance.

Findings

GiraffeDet outperforms previous SOTA models on multiple benchmarks.

The model achieves higher accuracy with less computational cost.

Dense multi-scale feature exchange enhances detection effectiveness.

Abstract

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. The source code is available at https://github.com/jyqi/GiraffeDet.