# Simultaneous Feature Aggregating and Hashing for Large-scale Image Search

arXiv: https://arxiv.org/abs/1704.00860 · HTML: https://mlsanity.com/paper/1704.00860/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2017.

## Built on by (most cited first, 5 of 5)

- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Contrastive Quantization with Code Memory for Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.05205/) (2021)
- [Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing](https://mlsanity.com/paper/2112.06489/) (2021)
- [Dsfer-Net: A Deep Supervision and Feature Retrieval Network for Bitemporal Change Detection Using Modern Hopfield Networks](https://mlsanity.com/paper/2304.01101/) (2023)
- [Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval](https://mlsanity.com/paper/2206.09806/) (2022)

## Abstract (arXiv)

In most state-of-the-art hashing-based visual search systems, local image descriptors of an image are first aggregated as a single feature vector. This feature vector is then subjected to a hashing function that produces a binary hash code. In previous work, the aggregating and the hashing processes are designed independently. In this paper, we propose a novel framework where feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization produces aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, we also propose a fast version of the recently-proposed Binary Autoencoder to be used in our proposed framework. We perform extensive retrieval experiments on several benchmark datasets with both SIFT and convolutional features. Our results suggest that the proposed framework achieves significant improvements over the state of the art.