Sunrise or Sunset: Selective Comparison Learning for Subtle Attribute Recognition

TL;DR

This paper introduces a novel pairwise learning approach for subtle attribute recognition, specifically distinguishing sunrise from sunset, and demonstrates its effectiveness on a new dataset and other tasks like temperature estimation.

Contribution

The paper proposes a new selective pairwise learning strategy for subtle attribute recognition, outperforming existing methods and achieving state-of-the-art results on related tasks.

Findings

Our method surpasses baseline accuracy significantly.

Achieves better results than humans in sunrise-sunset classification.

Sets new state-of-the-art in temperature estimation.

Abstract

The difficulty of image recognition has gradually increased from general category recognition to fine-grained recognition and to the recognition of some subtle attributes such as temperature and geolocation. In this paper, we try to focus on the classification between sunrise and sunset and hope to give a hint about how to tell the difference in subtle attributes. Sunrise vs. sunset is a difficult recognition task, which is challenging even for humans. Towards understanding this new problem, we first collect a new dataset made up of over one hundred webcams from different places. Since existing algorithmic methods have poor accuracy, we propose a new pairwise learning strategy to learn features from selective pairs of images. Experiments show that our approach surpasses baseline methods by a large margin and achieves better results even compared with humans. We also apply our approach to existing subtle attribute recognition problems, such as temperature estimation, and achieve state-of-the-art results.