Incremental Few-Shot Learning for Pedestrian Attribute Recognition

TL;DR

This paper introduces a meta learning framework for incremental few-shot pedestrian attribute recognition, enabling models to adapt to new attributes with limited data in surveillance scenarios.

Contribution

It proposes a novel meta architecture that disentangles attribute information and generalizes quickly to new attributes, addressing a key limitation of existing methods.

Findings

Achieves competitive performance on PETA and RAP datasets.

Requires low resources for incremental learning.

Effective in real-world surveillance scenarios.

Abstract

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.