Unsupervised visible-infrared person re-identification (UVI-ReID) aims at retrieving pedestrian images of the same individual across distinct modalities, presenting challenges due to the inherent heterogeneity gap and the absence of cost-prohibitive annotations. Although existing methods employ self-training with clustering-generated pseudo-labels to bridge this gap, they always implicitly assume that these pseudo-labels are predicted correctly. In practice, however, this presumption is impossible to satisfy due to the difficulty of training a perfect model let alone without any ground truths, resulting in pseudo-labeling errors. Based on the observation, this study introduces a new learning paradigm for UVI-ReID considering Pseudo-Label Noise (PLN), which encompasses three challenges: noise overfitting, error accumulation, and noisy cluster correspondence. To conquer these challenges, we propose a novel robust duality learning framework (RoDE) for UVI-ReID to mitigate the adverse impact of noisy pseudo-labels. Specifically, for noise overfitting, we propose a novel Robust Adaptive Learning mechanism (RAL) to dynamically prioritize clean samples while deprioritizing noisy ones, thus avoiding overemphasizing noise. To circumvent error accumulation of self-training, where the model tends to confirm its mistakes, RoDE alternately trains dual distinct models using pseudo-labels predicted by their counterparts, thereby maintaining diversity and avoiding collapse into noise. However, this will lead to cross-cluster misalignment between the two distinct models, not to mention the misalignment between different modalities, resulting in dual noisy cluster correspondence and thus difficult to optimize. To address this issue, a Cluster Consistency Matching mechanism (CCM) is presented to ensure reliable alignment across distinct modalities as well as across different models by leveraging cross-cluster similarities. Extensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed RoDE.

This paper discusses the face de-identification without losing facial attribute information and provides a solution called SF-GAN (Secret Face Generative Adversarial Network). The proposed model aims to realize face de-identification effectively and generate visually reasonable images while retaining the facial attribute information of original images, such as facial expression, gender, hairstyle and wearing glasses or not, as much as possible. To optimize the face de-identification, we construct a variety of external mechanisms to balance the influence of multiple factors on the effect of face de-identification. The SF-GAN differs from the face replacement and face swapping because the later two fails actually in the privacy protection. As for the multi-attribute retention, we use the shallow face attribute information and deep face attribute information, and adopt different processing strategies for different face attribute information based on the uniqueness of each kind of face attribute information. Finally, we train and test the model on two high-definition datasets Celeba-HQ and FFHD. Compared with existing face de-identification methods, the proposed model proved to perform better in protecting the facial privacy.

The rise of the metaverse and the increasing volume of heterogeneous 2D and 3D data have led to a growing demand for cross-modal retrieval, which allows users to query semantically relevant data across different modalities. Existing methods heavily rely on class labels to bridge semantic correlations, but it is expensive or even impossible to collect large-scale welll-abeled data in practice, thus making unsupervised learning more attractive and practical. However, unsupervised cross-modal learning is challenging to bridge semantic correlations across different modalities due to the lack of label information, which inevitably leads to unreliable discrimination. Based on the observations, we reveal and study a novel problem in this paper, namely unsupervised cross-modal learning with noisy pseudo labels. To address this problem, we propose a 2D-3D unsupervised multimodal learning framework that harnesses multimodal data. Our framework consists of three key components: 1) Self-matching Supervision Mechanism (SSM) warms up the model to encapsulate discrimination into the representations in a self-supervised learning manner. 2) Robust Discriminative Learning (RDL) further mines the discrimination from the learned imperfect predictions after warming up. To tackle the noise in the predicted pseudo labels, RDL leverages a novel Robust Concentrating Learning Loss (RCLL) to alleviate the influence of the uncertain samples, thus embracing robustness against noisy pseudo labels. 3) Modality-invariance Learning Mechanism (MLM) minimizes the cross-modal discrepancy to enforce SSM and RDL to produce common representations. We perform comprehensive experiments on four 2D-3D multimodal datasets, comparing our method against 14 state-of-the-art approaches, thereby demonstrating its effectiveness and superiority.

With the massive emergence of multi-modal data, cross-modal retrieval (CMR) has become one of the hot topics. Thanks to fast retrieval and efficient storage, cross-modal hashing (CMH) provides a feasible solution for large-scale multi-modal data. Previous CMH methods always directly learn common hash codes to fuse different modalities. Although they have obtained some success, there are still some limitations: 1) These approaches often prioritize reducing the heterogeneity in multi-modal data by learning consensus hash codes, yet they could sacrifice modality-specific information. 2) They frequently utilize pairwise similarities to guide hashing learning and neglect class distribution correlations. To overcome these two issues, we propose a novel Distribution Consistency Guided Hashing (DCGH) framework. Specifically, we first learn the modality-specific representation to extract the private discriminative information. Further, we learn consensus hash codes from the private representation by consensus hashing learning, thereby merging the specifics with consistency. Finally, we propose distribution consistency learning to guide hash codes following a similar class distribution principle between multi-modal data, thereby exploring more consistent information. Lots of experimental results on four benchmark datasets demonstrate the effectiveness of our DCGH on both fully paired and partially paired CMR tasks. The code can be available at: https://github.com/sunyuan-cs/2024-MM-DCGH.