PANDA: Pose Aligned Networks for Deep Attribute Modeling

TL;DR

This paper introduces a novel pose-normalized CNN approach that significantly improves human attribute classification accuracy in unconstrained images by combining part-based models with deep learning.

Contribution

The paper presents a new method that integrates pose normalization with CNNs, outperforming existing part-based and conventional CNN methods for attribute classification.

Findings

Outperforms state-of-the-art methods on challenging attribute classification tasks.

Demonstrates significant improvement over traditional CNNs and part-based models.

Effective in unconstrained, real-world settings with pose and viewpoint variations.

Abstract

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion. Convolutional Neural Nets (CNN) have been shown to perform very well on large scale object recognition problems. In the context of attribute classification, however, the signal is often subtle and it may cover only a small part of the image, while the image is dominated by the effects of pose and viewpoint. Discounting for pose variation would require training on very large labeled datasets which are not presently available. Part-based models, such as poselets and DPM have been shown to perform well for this problem but they are limited by shallow low-level features. We propose a new method which combines part-based models and deep learning by training pose-normalized CNNs. We show substantial improvement vs. state-of-the-art methods on challenging attribute classification tasks in unconstrained settings. Experiments confirm that our method outperforms both the best part-based methods on this problem and conventional CNNs trained on the full bounding box of the person.