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

TL;DR

This paper introduces RSHNL, a robust cross-modal hashing method that mimics human learning to effectively handle noisy labels, improving retrieval accuracy in large-scale, real-world datasets.

Contribution

It proposes a novel combination of contrastive hashing, center aggregation, and noise-tolerance self-paced learning to mitigate noisy labels in cross-modal retrieval.

Findings

RSHNL outperforms state-of-the-art methods in noisy label scenarios.

The noise-tolerance self-paced component effectively identifies and mitigates noisy labels.

Extensive experiments validate the robustness and effectiveness of the proposed approach.

Abstract

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.