Instance-Aware Hashing for Multi-Label Image Retrieval

TL;DR

This paper introduces a novel deep architecture for multi-label image retrieval that learns instance-aware representations, enabling both semantic and category-aware hashing, which significantly improves retrieval performance on benchmark datasets.

Contribution

It proposes a new deep network architecture that learns instance-aware, multi-group features for multi-label images, enhancing hashing methods for image retrieval.

Findings

Significant improvement over state-of-the-art hashing methods.

Effective for both semantic and category-aware hashing.

Demonstrated on multiple benchmark datasets.

Abstract

Similarity-preserving hashing is a commonly used method for nearest neighbour search in large-scale image retrieval. For image retrieval, deep-networks-based hashing methods are appealing since they can simultaneously learn effective image representations and compact hash codes. This paper focuses on deep-networks-based hashing for multi-label images, each of which may contain objects of multiple categories. In most existing hashing methods, each image is represented by one piece of hash code, which is referred to as semantic hashing. This setting may be suboptimal for multi-label image retrieval. To solve this problem, we propose a deep architecture that learns \textbf{instance-aware} image representations for multi-label image data, which are organized in multiple groups, with each group containing the features for one category. The instance-aware representations not only bring advantages to semantic hashing, but also can be used in category-aware hashing, in which an image is represented by multiple pieces of hash codes and each piece of code corresponds to a category. Extensive evaluations conducted on several benchmark datasets demonstrate that, for both semantic hashing and category-aware hashing, the proposed method shows substantial improvement over the state-of-the-art supervised and unsupervised hashing methods.