Xin-Shun Xu

Yu-Wei Zhan, Fan Liu, Xin Luo et al.

Human-Object Interaction (HOI) detection aims at detecting human-object pairs and predicting their interactions. However, conventional HOI detection methods often struggle to fully capture the contextual information needed to accurately identify these interactions. While large Vision-Language Models (VLMs) show promise in tasks involving human interactions, they are not tailored for HOI detection. The complexity of human behavior and the diverse contexts in which these interactions occur make it further challenging. Contextual cues, such as the participants involved, body language, and the surrounding environment, play crucial roles in predicting these interactions, especially those that are unseen or ambiguous. Moreover, large VLMs are trained on vast image and text data, enabling them to generate contextual cues that help in understanding real-world contexts, object relationships, and typical interactions. Building on this, in this paper we introduce ConCue, a novel approach for improving visual feature extraction in HOI detection. Specifically, we first design specialized prompts to utilize large VLMs to generate contextual cues within an image. To fully leverage these cues, we develop a transformer-based feature extraction module with a multi-tower architecture that integrates contextual cues into both instance and interaction detectors. Extensive experiments and analyses demonstrate the effectiveness of using these contextual cues for HOI detection. The experimental results show that integrating ConCue with existing state-of-the-art methods significantly enhances their performance on two widely used datasets.

Zi-Chao Zhang, Zhen-Duo Chen, Yongxin Wang et al.

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC tasks.However, there are some limitations when applying ViT directly to FGVC.First, ViT needs to split images into patches and calculate the attention of every pair, which may result in heavy redundant calculation and unsatisfying performance when handling fine-grained images with complex background and small objects.Second, a standard ViT only utilizes the class token in the final layer for classification, which is not enough to extract comprehensive fine-grained information. To address these issues, we propose a novel ViT based fine-grained object discriminator for FGVC tasks, ViT-FOD for short. Specifically, besides a ViT backbone, it further introduces three novel components, i.e, Attention Patch Combination (APC), Critical Regions Filter (CRF), and Complementary Tokens Integration (CTI). Thereinto, APC pieces informative patches from two images to generate a new image so that the redundant calculation can be reduced. CRF emphasizes tokens corresponding to discriminative regions to generate a new class token for subtle feature learning. To extract comprehensive information, CTI integrates complementary information captured by class tokens in different ViT layers. We conduct comprehensive experiments on widely used datasets and the results demonstrate that ViT-FOD is able to achieve state-of-the-art performance.

Xin Luo, Fang-Yi Liang, Jiale Liu et al.

As Web technology continues to develop, it has become increasingly common to use data stored on different clients. At the same time, federated learning has received widespread attention due to its ability to protect data privacy when let models learn from data which is distributed across various clients. However, most existing works assume that the client's data are fixed. In real-world scenarios, such an assumption is most likely not true as data may be continuously generated and new classes may also appear. To this end, we focus on the practical and challenging federated class-incremental learning (FCIL) problem. For FCIL, the local and global models may suffer from catastrophic forgetting on old classes caused by the arrival of new classes and the data distributions of clients are non-independent and identically distributed (non-iid). In this paper, we propose a novel method called Federated Class-Incremental Learning with PrompTing (FCILPT). Given the privacy and limited memory, FCILPT does not use a rehearsal-based buffer to keep exemplars of old data. We choose to use prompts to ease the catastrophic forgetting of the old classes. Specifically, we encode the task-relevant and task-irrelevant knowledge into prompts, preserving the old and new knowledge of the local clients and solving the problem of catastrophic forgetting. We first sort the task information in the prompt pool in the local clients to align the task information on different clients before global aggregation. It ensures that the same task's knowledge are fully integrated, solving the problem of non-iid caused by the lack of classes among different clients in the same incremental task. Experiments on CIFAR-100, Mini-ImageNet, and Tiny-ImageNet demonstrate that FCILPT achieves significant accuracy improvements over the state-of-the-art methods.

Jiale Liu, Yu-Wei Zhan, Xin Luo et al.

Recently, deep cross-modal hashing has gained increasing attention. However, in many practical cases, data are distributed and cannot be collected due to privacy concerns, which greatly reduces the cross-modal hashing performance on each client. And due to the problems of statistical heterogeneity, model heterogeneity, and forcing each client to accept the same parameters, applying federated learning to cross-modal hash learning becomes very tricky. In this paper, we propose a novel method called prototype-based layered federated cross-modal hashing. Specifically, the prototype is introduced to learn the similarity between instances and classes on server, reducing the impact of statistical heterogeneity (non-IID) on different clients. And we monitor the distance between local and global prototypes to further improve the performance. To realize personalized federated learning, a hypernetwork is deployed on server to dynamically update different layers' weights of local model. Experimental results on benchmark datasets show that our method outperforms state-of-the-art methods.

Yan Wang, Xin Luo, Zhen-Duo Chen et al.

Despite the great success achieved, existing video moment retrieval (VMR) methods are developed under the assumption that data are centralizedly stored. However, in real-world applications, due to the inherent nature of data generation and privacy concerns, data are often distributed on different silos, bringing huge challenges to effective large-scale training. In this work, we try to overcome above limitation by leveraging the recent success of federated learning. As the first that is explored in VMR field, the new task is defined as video moment retrieval with distributed data. Then, a novel federated learning method named FedVMR is proposed to facilitate large-scale and secure training of VMR models in decentralized environment. Experiments on benchmark datasets demonstrate its effectiveness. This work is the very first attempt to enable safe and efficient VMR training in decentralized scene, which is hoped to pave the way for further study in the related research field.

Yu-Wei Zhan, Xin Luo, Yongxin Wang et al.

The Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging task because of the large domain gap between sketches and natural images as well as the semantic inconsistency between seen and unseen categories. Previous literature bridges seen and unseen categories by semantic embedding, which requires prior knowledge of the exact class names and additional extraction efforts. And most works reduce domain gap by mapping sketches and natural images into a common high-level space using constructed sketch-image pairs, which ignore the unpaired information between images and sketches. To address these issues, in this paper, we propose a novel Three-Stream Joint Training Network (3JOIN) for the ZS-SBIR task. To narrow the domain differences between sketches and images, we extract edge maps for natural images and treat them as a bridge between images and sketches, which have similar content to images and similar style to sketches. For exploiting a sufficient combination of sketches, natural images, and edge maps, a novel three-stream joint training network is proposed. In addition, we use a teacher network to extract the implicit semantics of the samples without the aid of other semantics and transfer the learned knowledge to unseen classes. Extensive experiments conducted on two real-world datasets demonstrate the superiority of our proposed method.

Ming-Hui Liu, Harry Cheng, Xin Luo et al.

To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using available source domain data. However, predicting an unbounded set of future manipulations from limited prior examples is infeasible. To overcome this limitation, we propose to exploit the invariance of \textbf{real data} from two complementary perspectives: the fixed population distribution of the entire real class and the inherent Gaussianity of individual real images. Building on these properties, we introduce the Real Distribution Bias Correction (RDBC) framework, which consists of two key components: the Real Population Distribution Estimation module and the Distribution-Sampled Feature Whitening module. The former utilizes the independent and identically distributed (\iid) property of real samples to derive the normal distribution form of their statistics, from which the distribution parameters can be estimated using limited source domain data. Based on the learned population distribution, the latter utilizes the inherent Gaussianity of real data as a discriminative prior and performs a sampling-based whitening operation to amplify the Gaussianity gap between real and fake samples. Through synergistic coupling of the two modules, our model captures the real-world properties of real samples, thereby enhancing its generalizability to unseen target domains. Extensive experiments demonstrate that RDBC achieves state-of-the-art performance in both in-domain and cross-domain deepfake detection.

Hong Han, Hao-Chen Pei, Zhao-Zheng Nie et al.

Automatic pronunciation assessment plays a crucial role in computer-assisted pronunciation training systems. Due to the ability to perform multiple pronunciation tasks simultaneously, multi-aspect multi-granularity pronunciation assessment methods are gradually receiving more attention and achieving better performance than single-level modeling tasks. However, existing methods only consider unidirectional dependencies between adjacent granularity levels, lacking bidirectional interaction among phoneme, word, and utterance levels and thus insufficiently capturing the acoustic structural correlations. To address this issue, we propose a novel residual hierarchical interactive method, HIA for short, that enables bidirectional modeling across granularities. As the core of HIA, the Interactive Attention Module leverages an attention mechanism to achieve dynamic bidirectional interaction, effectively capturing linguistic features at each granularity while integrating correlations between different granularity levels. We also propose a residual hierarchical structure to alleviate the feature forgetting problem when modeling acoustic hierarchies. In addition, we use 1-D convolutional layers to enhance the extraction of local contextual cues at each granularity. Extensive experiments on the speechocean762 dataset show that our model is comprehensively ahead of the existing state-of-the-art methods.

Jingkuan Song, Xiaosu Zhu, Lianli Gao et al.

Quantization has been an effective technology in ANN (approximate nearest neighbour) search due to its high accuracy and fast search speed. To meet the requirement of different applications, there is always a trade-off between retrieval accuracy and speed, reflected by variable code lengths. However, to encode the dataset into different code lengths, existing methods need to train several models, where each model can only produce a specific code length. This incurs a considerable training time cost, and largely reduces the flexibility of quantization methods to be deployed in real applications. To address this issue, we propose a Deep Recurrent Quantization (DRQ) architecture which can generate sequential binary codes. To the end, when the model is trained, a sequence of binary codes can be generated and the code length can be easily controlled by adjusting the number of recurrent iterations. A shared codebook and a scalar factor is designed to be the learnable weights in the deep recurrent quantization block, and the whole framework can be trained in an end-to-end manner. As far as we know, this is the first quantization method that can be trained once and generate sequential binary codes. Experimental results on the benchmark datasets show that our model achieves comparable or even better performance compared with the state-of-the-art for image retrieval. But it requires significantly less number of parameters and training times. Our code is published online: https://github.com/cfm-uestc/DRQ.

Peng-Fei Zhang, Zi Huang, Xin-Shun Xu et al.

Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods commonly overlook the possible co-existence of both corruptions, limiting the effectiveness and practicability of the model. In this paper, we develop an Effective and Robust Adversarial Training (ERAT) framework to simultaneously handle two types of corruption (i.e., data and label) without prior knowledge of their specifics. We propose a hybrid adversarial training surrounding multiple potential adversarial perturbations, alongside a semi-supervised learning based on class-rebalancing sample selection to enhance the resilience of the model for dual corruption. On the one hand, in the proposed adversarial training, the perturbation generation module learns multiple surrogate malicious data perturbations by taking a DNN model as the victim, while the model is trained to maintain semantic consistency between the original data and the hybrid perturbed data. It is expected to enable the model to cope with unpredictable perturbations in real-world data corruption. On the other hand, a class-rebalancing data selection strategy is designed to fairly differentiate clean labels from noisy labels. Semi-supervised learning is performed accordingly by discarding noisy labels. Extensive experiments demonstrate the superiority of the proposed ERAT framework.

Ming-Hui Liu, Xiao-Qian Liu, Xin Luo et al.

Deepfake attribution (DFA) aims to perform multiclassification on different facial manipulation techniques, thereby mitigating the detrimental effects of forgery content on the social order and personal reputations. However, previous methods focus only on method-specific clues, which easily lead to overfitting, while overlooking the crucial role of common forgery features. Additionally, they struggle to distinguish between uncertain novel classes in more practical open-world scenarios. To address these issues, in this paper we propose an innovative multi-DisentAnglement based conTrastive leArning framework, DATA, to enhance the generalization ability on novel classes for the open-world semi-supervised deepfake attribution (OSS-DFA) task. Specifically, since all generation techniques can be abstracted into a similar architecture, DATA defines the concept of 'Orthonormal Deepfake Basis' for the first time and utilizes it to disentangle method-specific features, thereby reducing the overfitting on forgery-irrelevant information. Furthermore, an augmented-memory mechanism is designed to assist in novel class discovery and contrastive learning, which aims to obtain clear class boundaries for the novel classes through instance-level disentanglements. Additionally, to enhance the standardization and discrimination of features, DATA uses bases contrastive loss and center contrastive loss as auxiliaries for the aforementioned modules. Extensive experimental evaluations show that DATA achieves state-of-the-art performance on the OSS-DFA benchmark, e.g., there are notable accuracy improvements in 2.55% / 5.7% under different settings, compared with the existing methods.

Ming-Hui Liu, Harry Cheng, Tianyi Wang et al.

Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited understanding of real faces. To address this challenge, we propose a novel approach RealID to enhance generalization by learning a comprehensive concept of real faces while assessing the probabilities of belonging to the real and fake classes independently. RealID comprises two key modules: the Real Concept Capture Module (RealC2) and the Independent Dual-Decision Classifier (IDC). With the assistance of a MultiReal Memory, RealC2 maintains various prototypes for real faces, allowing the model to capture a comprehensive concept of real class. Meanwhile, IDC redefines the classification strategy by making independent decisions based on the concept of the real class and the presence of forgery artifacts. Through the combined effect of the above modules, the influence of forgery-irrelevant patterns is alleviated, and extensive experiments on five widely used datasets demonstrate that RealID significantly outperforms existing state-of-the-art methods, achieving a 1.74% improvement in average accuracy.

Li-Jun Zhao, Zhen-Duo Chen, Zi-Chao Zhang et al.

Few-shot class-incremental learning (FSCIL) aims at recognizing novel classes continually with limited novel class samples. A mainstream baseline for FSCIL is first to train the whole model in the base session, then freeze the feature extractor in the incremental sessions. Despite achieving high overall accuracy, most methods exhibit notably low accuracy for incremental classes. Some recent methods somewhat alleviate the accuracy imbalance between base and incremental classes by fine-tuning the feature extractor in the incremental sessions, but they further cause the accuracy imbalance between past and current incremental classes. In this paper, we study the causes of such classification accuracy imbalance for FSCIL, and abstract them into a unified model bias problem. Based on the analyses, we propose a novel method to mitigate model bias of the FSCIL problem during training and inference processes, which includes mapping ability stimulation, separately dual-feature classification, and self-optimizing classifiers. Extensive experiments on three widely-used FSCIL benchmark datasets show that our method significantly mitigates the model bias problem and achieves state-of-the-art performance.

Ming-Hui Liu, Harry Cheng, Xin Luo et al.

Robust deepfake detection models must be capable of generalizing to ever-evolving manipulation techniques beyond training data. A promising strategy is to augment the training data with online synthesized fake images containing broadly generalizable artifacts. However, in the context of deepfake detection, it is surprising that jointly training on both original and online synthesized forgeries may result in degraded performance. This contradicts the common belief that incorporating more source-domain data should enhance detection accuracy. Through empirical analysis, we trace this degradation to gradient conflicts during backpropagation which force a trade-off between source domain accuracy and target domain generalization. To overcome this issue, we propose a Conflict-Suppressed Deepfake Detection (CS-DFD) framework that explicitly mitigates the gradient conflict via two synergistic modules. First, an Update Vector Search (UVS) module searches for an alternative update vector near the initial gradient vector to reconcile the disparities of the original and online synthesized forgeries. By further transforming the search process into an extremum optimization problem, UVS yields the uniquely update vector, which maximizes the simultaneous loss reductions for each data type. Second, a Conflict Gradient Reduction (CGR) module enforces a low-conflict feature embedding space through a novel Conflict Descent Loss. This loss penalizes misaligned gradient directions and guides the learning of representations with aligned, non-conflicting gradients. The synergy of UVS and CGR alleviates gradient interference in both parameter optimization and representation learning. Experiments on multiple deepfake benchmarks demonstrate that CS-DFD achieves state-of-the-art performance in both in-domain detection accuracy and cross-domain generalization.

Li-Jun Zhao, Zhen-Duo Chen, Zhi-Yuan Xue et al.

Current fine-grained classification research primarily focuses on fine-grained feature learning. However, in real-world scenarios, fine-grained data annotation is challenging, and the features and semantics are highly diverse and frequently changing. These issues create inherent barriers between traditional experimental settings and real-world applications, limiting the effectiveness of conventional fine-grained classification methods. Although some recent studies have provided potential solutions to these issues, most of them still rely on limited supervised information and thus fail to offer effective solutions. In this paper, based on theoretical analysis, we propose a novel learning paradigm to break the barriers in fine-grained classification. This paradigm enables the model to progressively learn during inference, thereby leveraging cost-free data to more accurately represent fine-grained categories and adapt to dynamic semantic changes. On this basis, an efficient EXPloring and EXPloiting strategy and method (EXP2) is designed. Thereinto, useful inference data samples are explored according to class representations and exploited to optimize classifiers. Experimental results demonstrate the general effectiveness of our method, providing guidance for future in-depth understanding and exploration of real-world fine-grained classification.

Tian-Zi Niu, Zhen-Duo Chen, Xin Luo et al.

Conventional approaches for video captioning leverage a variety of offline-extracted features to generate captions. Despite the availability of various offline-feature-extractors that offer diverse information from different perspectives, they have several limitations due to fixed parameters. Concretely, these extractors are solely pre-trained on image/video comprehension tasks, making them less adaptable to video caption datasets. Additionally, most of these extractors only capture features prior to the classifier of the pre-training task, ignoring a significant amount of valuable shallow information. Furthermore, employing multiple offline-features may introduce redundant information. To address these issues, we propose an end-to-end encoder-decoder-based network (EVC-MF) for video captioning, which efficiently utilizes multi-scale visual and textual features to generate video descriptions. Specifically, EVC-MF consists of three modules. Firstly, instead of relying on multiple feature extractors, we directly feed video frames into a transformer-based network to obtain multi-scale visual features and update feature extractor parameters. Secondly, we fuse the multi-scale features and input them into a masked encoder to reduce redundancy and encourage learning useful features. Finally, we utilize an enhanced transformer-based decoder, which can efficiently leverage shallow textual information, to generate video descriptions. To evaluate our proposed model, we conduct extensive experiments on benchmark datasets. The results demonstrate that EVC-MF yields competitive performance compared with the state-of-theart methods.

Xiao-Ming Wu, Xin Luo, Yu-Wei Zhan et al.

With the vigorous development of multimedia equipment and applications, efficient retrieval of large-scale multi-modal data has become a trendy research topic. Thereinto, hashing has become a prevalent choice due to its retrieval efficiency and low storage cost. Although multi-modal hashing has drawn lots of attention in recent years, there still remain some problems. The first point is that existing methods are mainly designed in batch mode and not able to efficiently handle streaming multi-modal data. The second point is that all existing online multi-modal hashing methods fail to effectively handle unseen new classes which come continuously with streaming data chunks. In this paper, we propose a new model, termed Online enhAnced SemantIc haShing (OASIS). We design novel semantic-enhanced representation for data, which could help handle the new coming classes, and thereby construct the enhanced semantic objective function. An efficient and effective discrete online optimization algorithm is further proposed for OASIS. Extensive experiments show that our method can exceed the state-of-the-art models. For good reproducibility and benefiting the community, our code and data are already available in supplementary material and will be made publicly available.

Yu-Wei Zhan, Xin Luo, Yu Sun et al.

With the rapid development of social websites, recent years have witnessed an explosive growth of social images with user-provided tags which continuously arrive in a streaming fashion. Due to the fast query speed and low storage cost, hashing-based methods for image search have attracted increasing attention. However, existing hashing methods for social image retrieval are based on batch mode which violates the nature of social images, i.e., social images are usually generated periodically or collected in a stream fashion. Although there exist many online image hashing methods, they either adopt unsupervised learning which ignore the relevant tags, or are designed in the supervised manner which needs high-quality labels. In this paper, to overcome the above limitations, we propose a new method named Weakly-supervised Online Hashing (WOH). In order to learn high-quality hash codes, WOH exploits the weak supervision by considering the semantics of tags and removing the noise. Besides, We develop a discrete online optimization algorithm for WOH, which is efficient and scalable. Extensive experiments conducted on two real-world datasets demonstrate the superiority of WOH compared with several state-of-the-art hashing baselines.

Jianfeng Wang, Jingdong Wang, Jingkuan Song et al.

Product quantization-based approaches are effective to encode high-dimensional data points for approximate nearest neighbor search. The space is decomposed into a Cartesian product of low-dimensional subspaces, each of which generates a sub codebook. Data points are encoded as compact binary codes using these sub codebooks, and the distance between two data points can be approximated efficiently from their codes by the precomputed lookup tables. Traditionally, to encode a subvector of a data point in a subspace, only one sub codeword in the corresponding sub codebook is selected, which may impose strict restrictions on the search accuracy. In this paper, we propose a novel approach, named Optimized Cartesian $K$-Means (OCKM), to better encode the data points for more accurate approximate nearest neighbor search. In OCKM, multiple sub codewords are used to encode the subvector of a data point in a subspace. Each sub codeword stems from different sub codebooks in each subspace, which are optimally generated with regards to the minimization of the distortion errors. The high-dimensional data point is then encoded as the concatenation of the indices of multiple sub codewords from all the subspaces. This can provide more flexibility and lower distortion errors than traditional methods. Experimental results on the standard real-life datasets demonstrate the superiority over state-of-the-art approaches for approximate nearest neighbor search.