# Feature Pyramid Hashing

## TL;DR

This paper introduces a two-pyramid hashing architecture that combines high-level semantic features with low-level details for improved fine-grained image retrieval, outperforming existing methods.

## Contribution

It proposes a novel two-pyramid structure and a consensus fusion strategy to effectively capture both semantic and subtle appearance details in deep hashing.

## Key findings

- Significant improvement over state-of-the-art on CUB-200-2011 dataset.
- Effective capture of subtle differences enhances fine-grained retrieval.
- Demonstrates the benefit of combining high and low-layer features.

## Abstract

In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval. Most deep hashing approaches use the high layer to extract the powerful semantic representations. However, these methods have limited ability for fine-grained image retrieval because the semantic features extracted from the high layer are difficult in capturing the subtle differences. To this end, we propose a novel two-pyramid hashing architecture to learn both the semantic information and the subtle appearance details for fine-grained image search. Inspired by the feature pyramids of convolutional neural network, a vertical pyramid is proposed to capture the high-layer features and a horizontal pyramid combines multiple low-layer features with structural information to capture the subtle differences. To fuse the low-level features, a novel combination strategy, called consensus fusion, is proposed to capture all subtle information from several low-layers for finer retrieval. Extensive evaluation on two fine-grained datasets CUB-200-2011 and Stanford Dogs demonstrate that the proposed method achieves significant performance compared with the state-of-art baselines.