# Deep Self-Adaptive Hashing for Image Retrieval

arXiv: https://arxiv.org/abs/2108.07094 · HTML: https://mlsanity.com/paper/2108.07094/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 16 of 16)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Deep Supervised Discrete Hashing](https://mlsanity.com/paper/1705.10999/) (2017)
- [Asymmetric Deep Supervised Hashing](https://mlsanity.com/paper/1707.08325/) (2017)
- [DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs](https://mlsanity.com/paper/1905.03465/) (2019)
- [Auto-Encoding Twin-Bottleneck Hashing](https://mlsanity.com/paper/2002.11930/) (2020)
- [Binary Generative Adversarial Networks for Image Retrieval](https://mlsanity.com/paper/1708.04150/) (2017)
- [Stochastic Generative Hashing](https://mlsanity.com/paper/1701.02815/) (2017)
- [Fast Supervised Discrete Hashing](https://mlsanity.com/paper/1904.03556/) (2019)
- [Deep Cross-Modal Hashing with Hashing Functions and Unified Hash Codes Jointly Learning](https://mlsanity.com/paper/1907.12490/) (2019)
- [Deep Semantic Hashing with Generative Adversarial Networks](https://mlsanity.com/paper/1804.08275/) (2018)
- [Cross-modal Zero-shot Hashing](https://mlsanity.com/paper/1908.07388/) (2019)
- [Object Detection based Deep Unsupervised Hashing](https://mlsanity.com/paper/1811.09822/) (2018)

## Built on by (most cited first, 3 of 3)

- [Unsupervised Hashing with Semantic Concept Mining](https://mlsanity.com/paper/2209.11475/) (2022)
- [Multimodal semantic retrieval for product search](https://mlsanity.com/paper/2501.07365/) (2025)
- [Deep Unsupervised Hashing with Latent Semantic Components](https://mlsanity.com/paper/2203.09420/) (2022)

## Abstract (arXiv)

Hashing technology has been widely used in image retrieval due to its computational and storage efficiency. Recently, deep unsupervised hashing methods have attracted increasing attention due to the high cost of human annotations in the real world and the superiority of deep learning technology. However, most deep unsupervised hashing methods usually pre-compute a similarity matrix to model the pairwise relationship in the pre-trained feature space. Then this similarity matrix would be used to guide hash learning, in which most of the data pairs are treated equivalently. The above process is confronted with the following defects: 1) The pre-computed similarity matrix is inalterable and disconnected from the hash learning process, which cannot explore the underlying semantic information. 2) The informative data pairs may be buried by the large number of less-informative data pairs. To solve the aforementioned problems, we propose a Deep Self-Adaptive Hashing (DSAH) model to adaptively capture the semantic information with two special designs: Adaptive Neighbor Discovery (AND) and Pairwise Information Content (PIC). Firstly, we adopt the AND to initially construct a neighborhood-based similarity matrix, and then refine this initial similarity matrix with a novel update strategy to further investigate the semantic structure behind the learned representation. Secondly, we measure the priorities of data pairs with PIC and assign adaptive weights to them, which is relies on the assumption that more dissimilar data pairs contain more discriminative information for hash learning. Extensive experiments on several datasets demonstrate that the above two technologies facilitate the deep hashing model to achieve superior performance.