# Deep Hashing with Hash Center Update for Efficient Image Retrieval

arXiv: https://arxiv.org/abs/2106.06269 · HTML: https://mlsanity.com/paper/2106.06269/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2021.

## Built on by (most cited first, 4 of 4)

- [Prototype-Based Layered Federated Cross-Modal Hashing](https://mlsanity.com/paper/2210.15678/) (2022)
- [Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function](https://mlsanity.com/paper/2511.12162/) (2025)
- [Hashing Learning with Hyper-Class Representation](https://mlsanity.com/paper/2206.02334/) (2022)
- [Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token](https://mlsanity.com/paper/2607.03328/) (2026)

## Abstract (arXiv)

In this paper, we propose an approach for learning binary hash codes for image retrieval. Canonical Correlation Analysis (CCA) is used to design two loss functions for training a neural network such that the correlation between the two views to CCA is maximized. The first loss, maximizes the correlation between the hash centers and learned hash codes. The second loss maximizes the correlation between the class labels and classification scores. A novel weighted mean and thresholding based hash center update scheme is proposed for adapting the hash centers in each epoch. The training loss reaches the theoretical lower bound of the proposed loss functions, showing that the correlation coefficients are maximized during training and substantiating the formation of an efficient feature space for image retrieval. The measured mean average precision shows that the proposed approach outperforms other state-of-the-art approaches in both single-labeled and multi-labeled image datasets.