# Deep Lifelong Cross-modal Hashing

arXiv: https://arxiv.org/abs/2304.13357 · HTML: https://mlsanity.com/paper/2304.13357/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 73 references that are in the map.
- First posted on arXiv 26 Apr 2023.

## Builds on (most cited first, 19 of 19)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks](https://mlsanity.com/paper/2011.01844/) (2020)
- [Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks](https://mlsanity.com/paper/2203.17030/) (2022)
- [Deep Cross-Modal Hashing](https://mlsanity.com/paper/1602.02255/) (2016)
- [Efficient Feature Transformations for Discriminative and Generative Continual Learning](https://mlsanity.com/paper/2103.13558/) (2021)
- [A Survey on Deep Hashing Methods](https://mlsanity.com/paper/2003.03369/) (2020)
- [Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval](https://mlsanity.com/paper/1804.01223/) (2018)
- [An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges](https://mlsanity.com/paper/1704.02223/) (2017)
- [Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing](https://mlsanity.com/paper/2012.13538/) (2020)
- [Deep Binary Reconstruction for Cross-modal Hashing](https://mlsanity.com/paper/1708.05127/) (2017)
- [Deep Ordinal Hashing with Spatial Attention](https://mlsanity.com/paper/1805.02459/) (2018)
- [Ranking-based Deep Cross-modal Hashing](https://mlsanity.com/paper/1905.04450/) (2019)
- [Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing](https://mlsanity.com/paper/2112.06489/) (2021)
- [Unsupervised Deep Cross-modality Spectral Hashing](https://mlsanity.com/paper/2008.00223/) (2020)

## Abstract (arXiv)

Hashing methods have made significant progress in cross-modal retrieval tasks with fast query speed and low storage cost. Among them, deep learning-based hashing achieves better performance on large-scale data due to its excellent extraction and representation ability for nonlinear heterogeneous features. However, there are still two main challenges in catastrophic forgetting when data with new categories arrive continuously, and time-consuming for non-continuous hashing retrieval to retrain for updating. To this end, we, in this paper, propose a novel deep lifelong cross-modal hashing to achieve lifelong hashing retrieval instead of re-training hash function repeatedly when new data arrive. Specifically, we design lifelong learning strategy to update hash functions by directly training the incremental data instead of retraining new hash functions using all the accumulated data, which significantly reduce training time. Then, we propose lifelong hashing loss to enable original hash codes participate in lifelong learning but remain invariant, and further preserve the similarity and dis-similarity among original and incremental hash codes to maintain performance. Additionally, considering distribution heterogeneity when new data arriving continuously, we introduce multi-label semantic similarity to supervise hash learning, and it has been proven that the similarity improves performance with detailed analysis. Experimental results on benchmark datasets show that the proposed methods achieves comparative performance comparing with recent state-of-the-art cross-modal hashing methods, and it yields substantial average increments over 20% in retrieval accuracy and almost reduces over 80% training time when new data arrives continuously.