Dynamic Head: Unifying Object Detection Heads with Attentions

TL;DR

This paper introduces a dynamic head framework that unifies various object detection heads with attention mechanisms, significantly enhancing detection performance and efficiency without added computational cost.

Contribution

The paper proposes a novel dynamic head that unifies detection heads using multiple self-attention mechanisms, improving representation and achieving state-of-the-art results.

Findings

Achieves 54.0 AP on COCO with ResNeXt-101-DCN backbone.

Sets a new record of 60.6 AP with transformer backbone and extra data.

Improves detection performance without additional computational overhead.

Abstract

The complex nature of combining localization and classification in object detection has resulted in the flourished development of methods. Previous works tried to improve the performance in various object detection heads but failed to present a unified view. In this paper, we present a novel dynamic head framework to unify object detection heads with attentions. By coherently combining multiple self-attention mechanisms between feature levels for scale-awareness, among spatial locations for spatial-awareness, and within output channels for task-awareness, the proposed approach significantly improves the representation ability of object detection heads without any computational overhead. Further experiments demonstrate that the effectiveness and efficiency of the proposed dynamic head on the COCO benchmark. With a standard ResNeXt-101-DCN backbone, we largely improve the performance over popular object detectors and achieve a new state-of-the-art at 54.0 AP. Furthermore, with latest transformer backbone and extra data, we can push current best COCO result to a new record at 60.6 AP. The code will be released at https://github.com/microsoft/DynamicHead.