Attribute Recognition by Joint Recurrent Learning of Context and Correlation

TL;DR

This paper introduces a Joint Recurrent Learning model that leverages attribute context and correlation to improve pedestrian attribute recognition in low-quality images with limited training data.

Contribution

The paper proposes a novel end-to-end recurrent network that jointly models attribute correlations and their sequential dependencies for better recognition.

Findings

JRL outperforms state-of-the-art models on PETA and RAP benchmarks.

The model demonstrates robustness with small training datasets.

It effectively captures high-order attribute correlations.

Abstract

Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small. In this work, we formulate a Joint Recurrent Learning (JRL) model for exploring attribute context and correlation in order to improve attribute recognition given small sized training data with poor quality images. The JRL model learns jointly pedestrian attribute correlations in a pedestrian image and in particular their sequential ordering dependencies (latent high-order correlation) in an end-to-end encoder/decoder recurrent network. We demonstrate the performance advantage and robustness of the JRL model over a wide range of state-of-the-art deep models for pedestrian attribute recognition, multi-label image classification, and multi-person image annotation on two largest pedestrian attribute benchmarks PETA and RAP.