# Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels

arXiv: https://arxiv.org/abs/2501.01699 · HTML: https://mlsanity.com/paper/2501.01699/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jan 2025.

## Built on by (most cited first, 10 of 10)

- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval](https://mlsanity.com/paper/2604.18037/) (2026)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval](https://mlsanity.com/paper/2604.21806/) (2026)
- [A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification](https://mlsanity.com/paper/2511.18677/) (2025)
- [Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval](https://mlsanity.com/paper/2511.07780/) (2025)
- [IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval](https://mlsanity.com/paper/2606.08144/) (2026)
- [Neighbor-aware Instance Refining with Noisy Labels for Cross-Modal Retrieval](https://mlsanity.com/paper/2512.24064/) (2025)
- [Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence](https://mlsanity.com/paper/2603.28134/) (2026)
- [RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval](https://mlsanity.com/paper/2606.11689/) (2026)

## Abstract (arXiv)

Cross-modal hashing (CMH) has appeared as a popular technique for cross-modal retrieval due to its low storage cost and high computational efficiency in large-scale data. Most existing methods implicitly assume that multi-modal data is correctly labeled, which is expensive and even unattainable due to the inevitable imperfect annotations (i.e., noisy labels) in real-world scenarios. Inspired by human cognitive learning, a few methods introduce self-paced learning (SPL) to gradually train the model from easy to hard samples, which is often used to mitigate the effects of feature noise or outliers. It is a less-touched problem that how to utilize SPL to alleviate the misleading of noisy labels on the hash model. To tackle this problem, we propose a new cognitive cross-modal retrieval method called Robust Self-paced Hashing with Noisy Labels (RSHNL), which can mimic the human cognitive process to identify the noise while embracing robustness against noisy labels. Specifically, we first propose a contrastive hashing learning (CHL) scheme to improve multi-modal consistency, thereby reducing the inherent semantic gap. Afterward, we propose center aggregation learning (CAL) to mitigate the intra-class variations. Finally, we propose Noise-tolerance Self-paced Hashing (NSH) that dynamically estimates the learning difficulty for each instance and distinguishes noisy labels through the difficulty level. For all estimated clean pairs, we further adopt a self-paced regularizer to gradually learn hash codes from easy to hard. Extensive experiments demonstrate that the proposed RSHNL performs remarkably well over the state-of-the-art CMH methods.