Generic Instance Search and Re-identification from One Example via Attributes and Categories

TL;DR

This paper introduces a novel approach for generic instance search from a single example using automatically learned category-specific attributes, significantly improving search accuracy across diverse object categories including shoes, cars, and persons.

Contribution

The paper proposes a new method leveraging category-specific attributes for generic instance search, outperforming existing methods and unifying person re-identification as a special case.

Findings

Attributes outperform existing methods on shoes and cars.

Achieves state-of-the-art results on VIPeR dataset for person re-identification.

Combining category-level info with attributes surpasses low-level feature methods.

Abstract

This paper aims for generic instance search from one example where the instance can be an arbitrary object like shoes, not just near-planar and one-sided instances like buildings and logos. First, we evaluate state-of-the-art instance search methods on this problem. We observe that what works for buildings loses its generality on shoes. Second, we propose to use automatically learned category-specific attributes to address the large appearance variations present in generic instance search. Searching among instances from the same category as the query, the category-specific attributes outperform existing approaches by a large margin on shoes and cars and perform on par with the state-of-the-art on buildings. Third, we treat person re-identification as a special case of generic instance search. On the popular VIPeR dataset, we reach state-of-the-art performance with the same method. Fourth, we extend our method to search objects without restriction to the specifically known category. We show that the combination of category-level information and the category-specific attributes is superior to the alternative method combining category-level information with low-level features such as Fisher vector.