A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images

by   Pierre Le Jeune, et al.

Few-Shot Object Detection (FSOD) methods are mainly designed and evaluated on natural image datasets such as Pascal VOC and MS COCO. However, it is not clear whether the best methods for natural images are also the best for aerial images. Furthermore, direct comparison of performance between FSOD methods is difficult due to the wide variety of detection frameworks and training strategies. Therefore, we propose a benchmarking framework that provides a flexible environment to implement and compare attention-based FSOD methods. The proposed framework focuses on attention mechanisms and is divided into three modules: spatial alignment, global attention, and fusion layer. To remain competitive with existing methods, which often leverage complex training, we propose new augmentation techniques designed for object detection. Using this framework, several FSOD methods are reimplemented and compared. This comparison highlights two distinct performance regimes on aerial and natural images: FSOD performs worse on aerial images. Our experiments suggest that small objects, which are harder to detect in the few-shot setting, account for the poor performance. Finally, we develop a novel multiscale alignment method, Cross-Scales Query-Support Alignment (XQSA) for FSOD, to improve the detection of small objects. XQSA outperforms the state-of-the-art significantly on DOTA and DIOR.


page 3

page 8

page 10

page 14

page 16

page 17

page 18


A Unified Framework for Attention-Based Few-Shot Object Detection

Few-Shot Object Detection (FSOD) is a rapidly growing field in computer ...

Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime

In Few-Shot Object Detection (FSOD), detecting small objects is extremel...

On the Robustness of Object Detection Models in Aerial Images

The robustness of object detection models is a major concern when applie...

Query-guided Attention in Vision Transformers for Localizing Objects Using a Single Sketch

In this work, we investigate the problem of sketch-based object localiza...

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 ...

Point RCNN: An Angle-Free Framework for Rotated Object Detection

Rotated object detection in aerial images is still challenging due to ar...

A Systematic Evaluation of Object Detection Networks for Scientific Plots

Are existing object detection methods adequate for detecting text and vi...

Please sign up or login with your details

Forgot password? Click here to reset