Dynamic Head: Unifying Object Detection Heads with Attentions

06/15/2021
by   Xiyang Dai, et al.
3

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.

READ FULL TEXT

page 3

page 6

research
02/18/2022

Task Specific Attention is one more thing you need for object detection

Various models have been proposed to solve the object detection problem....
research
12/14/2020

Decoupled Self Attention for Accurate One Stage Object Detection

As the scale of object detection dataset is smaller than that of image r...
research
02/24/2021

Should I Look at the Head or the Tail? Dual-awareness Attention for Few-Shot Object Detection

While recent progress has significantly boosted few-shot classification ...
research
05/07/2023

YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification

In this study, we examine the associations between channel features and ...
research
10/29/2020

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Existing object detection frameworks are usually built on a single forma...
research
07/20/2023

Cascade-DETR: Delving into High-Quality Universal Object Detection

Object localization in general environments is a fundamental part of vis...
research
08/26/2021

TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios

Object detection on drone-captured scenarios is a recent popular task. A...

Please sign up or login with your details

Forgot password? Click here to reset