Incremental Few-Shot Learning for Pedestrian Attribute Recognition
This addresses a practical issue in video surveillance for incremental attribute updates, but it is incremental as it builds on existing meta-learning approaches.
The paper tackles the problem of adapting pedestrian attribute recognition models to newly added attributes with scarce data, achieving competitive performance and low resource requirements on benchmark datasets PETA and RAP.
Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a fixed set of attributes. They are unable to handle the incremental few-shot learning scenario, i.e. adapting a well-trained model to newly added attributes with scarce data, which commonly exists in the real world. In this work, we present a meta learning based method to address this issue. The core of our framework is a meta architecture capable of disentangling multiple attribute information and generalizing rapidly to new coming attributes. By conducting extensive experiments on the benchmark dataset PETA and RAP under the incremental few-shot setting, we show that our method is able to perform the task with competitive performances and low resource requirements.