# Instance-weighted Central Similarity for Multi-label Image Retrieval

arXiv: https://arxiv.org/abs/2108.05274 · HTML: https://mlsanity.com/paper/2108.05274/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 11 Aug 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (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)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application](https://mlsanity.com/paper/1309.1541/) (2013)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [A Survey on Deep Hashing Methods](https://mlsanity.com/paper/2003.03369/) (2020)
- [Simultaneous Feature Learning and Hash Coding with Deep Neural Networks](https://mlsanity.com/paper/1504.03410/) (2015)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Deep Supervised Hashing with Triplet Labels](https://mlsanity.com/paper/1612.03900/) (2016)
- [Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval](https://mlsanity.com/paper/1501.06272/) (2015)
- [Instance-Aware Hashing for Multi-Label Image Retrieval](https://mlsanity.com/paper/1603.03234/) (2016)
- [Supervised Online Hashing via Hadamard Codebook Learning](https://mlsanity.com/paper/1905.03694/) (2019)
- [Hadamard Matrix Guided Online Hashing](https://mlsanity.com/paper/1905.04454/) (2019)
- [Towards Optimal Discrete Online Hashing with Balanced Similarity](https://mlsanity.com/paper/1901.10185/) (2019)
- [Hadamard Codebook Based Deep Hashing](https://mlsanity.com/paper/1910.09182/) (2019)

## Built on by (most cited first, 6 of 6)

- [Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels](https://mlsanity.com/paper/2203.02172/) (2022)
- [Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels](https://mlsanity.com/paper/2205.11131/) (2022)
- [Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels](https://mlsanity.com/paper/2205.13092/) (2022)
- [Learning Semantic-Aware Representation in Visual-Language Models for Multi-Label Recognition with Partial Labels](https://mlsanity.com/paper/2412.10843/) (2024)
- [Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding](https://mlsanity.com/paper/2210.07572/) (2022)
- [Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels](https://mlsanity.com/paper/2507.23263/) (2025)

## Abstract (arXiv)

Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the above issue, we propose a two-step alternative optimization approach, Instance-weighted Central Similarity (ICS), to automatically learn the center weight corresponding to a hash code. Firstly, we apply the maximum entropy regularizer to prevent one hash center from dominating the loss function, and compute the center weights via projection gradient descent. Secondly, we update neural network parameters by standard back-propagation with fixed center weights. More importantly, the learned center weights can well reflect the proportion of foreground instances in the image. Our method achieves the state-of-the-art performance on the image retrieval benchmarks, and especially improves the mAP by 1.6%-6.4% on the MS COCO dataset.