A Unified Framework for Attention-Based Few-Shot Object Detection
This work addresses a benchmarking problem for researchers in computer vision, but it is incremental as it focuses on comparison rather than introducing new methods.
The authors tackled the difficulty in comparing attention-based few-shot object detection methods by proposing a flexible framework that standardizes implementations, enabling direct performance comparisons of different attention mechanisms with fixed parameters.
Few-Shot Object Detection (FSOD) is a rapidly growing field in computer vision. It consists in finding all occurrences of a given set of classes with only a few annotated examples for each class. Numerous methods have been proposed to address this challenge and most of them are based on attention mechanisms. However, the great variety of classic object detection frameworks and training strategies makes performance comparison between methods difficult. In particular, for attention-based FSOD methods, it is laborious to compare the impact of the different attention mechanisms on performance. This paper aims at filling this shortcoming. To do so, a flexible framework is proposed to allow the implementation of most of the attention techniques available in the literature. To properly introduce such a framework, a detailed review of the existing FSOD methods is firstly provided. Some different attention mechanisms are then reimplemented within the framework and compared with all other parameters fixed.