Weifeng Liu

Jun Rao, Fei Wang, Liang Ding et al.

This article aims to provide the information retrieval community with some reflections on recent advances in retrieval learning by analyzing the reproducibility of image-text retrieval models. Due to the increase of multimodal data over the last decade, image-text retrieval has steadily become a major research direction in the field of information retrieval. Numerous researchers train and evaluate image-text retrieval algorithms using benchmark datasets such as MS-COCO and Flickr30k. Research in the past has mostly focused on performance, with multiple state-of-the-art methodologies being suggested in a variety of ways. According to their assertions, these techniques provide improved modality interactions and hence more precise multimodal representations. In contrast to previous works, we focus on the reproducibility of the approaches and the examination of the elements that lead to improved performance by pretrained and nonpretrained models in retrieving images and text. To be more specific, we first examine the related reproducibility concerns and explain why our focus is on image-text retrieval tasks. Second, we systematically summarize the current paradigm of image-text retrieval models and the stated contributions of those approaches. Third, we analyze various aspects of the reproduction of pretrained and nonpretrained retrieval models. To complete this, we conducted ablation experiments and obtained some influencing factors that affect retrieval recall more than the improvement claimed in the original paper. Finally, we present some reflections and challenges that the retrieval community should consider in the future. Our source code is publicly available at https://github.com/WangFei-2019/Image-text-Retrieval.

Changtong Zan, Liang Ding, Li Shen et al.

Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT). However, it usually fails to achieve notable gains (sometimes, even worse) on resource-rich NMT on par with its Random-Initialization (RI) counterpart. We take the first step to investigate the complementarity between PT and RI in resource-rich scenarios via two probing analyses, and find that: 1) PT improves NOT the accuracy, but the generalization by achieving flatter loss landscapes than that of RI; 2) PT improves NOT the confidence of lexical choice, but the negative diversity by assigning smoother lexical probability distributions than that of RI. Based on these insights, we propose to combine their complementarities with a model fusion algorithm that utilizes optimal transport to align neurons between PT and RI. Experiments on two resource-rich translation benchmarks, WMT'17 English-Chinese (20M) and WMT'19 English-German (36M), show that PT and RI could be nicely complementary to each other, achieving substantial improvements considering both translation accuracy, generalization, and negative diversity. Probing tools and code are released at: https://github.com/zanchangtong/PTvsRI.

Rui Xu, Lei Xing, Shuai Shao et al.

Few-shot learning (FSL), purposing to resolve the problem of data-scarce, has attracted considerable attention in recent years. A popular FSL framework contains two phases: (i) the pre-train phase employs the base data to train a CNN-based feature extractor. (ii) the meta-test phase applies the frozen feature extractor to novel data (novel data has different categories from base data) and designs a classifier for recognition. To correct few-shot data distribution, researchers propose Semi-Supervised Few-Shot Learning (SSFSL) by introducing unlabeled data. Although SSFSL has been proved to achieve outstanding performances in the FSL community, there still exists a fundamental problem: the pre-trained feature extractor can not adapt to the novel data flawlessly due to the cross-category setting. Usually, large amounts of noises are introduced to the novel feature. We dub it as Feature-Extractor-Maladaptive (FEM) problem. To tackle FEM, we make two efforts in this paper. First, we propose a novel label prediction method, Isolated Graph Learning (IGL). IGL introduces the Laplacian operator to encode the raw data to graph space, which helps reduce the dependence on features when classifying, and then project graph representation to label space for prediction. The key point is that: IGL can weaken the negative influence of noise from the feature representation perspective, and is also flexible to independently complete training and testing procedures, which is suitable for SSFSL. Second, we propose Graph Co-Training (GCT) to tackle this challenge from a multi-modal fusion perspective by extending the proposed IGL to the co-training framework. GCT is a semi-supervised method that exploits the unlabeled samples with two modal features to crossly strengthen the IGL classifier.

Changtong Zan, Keqin Peng, Liang Ding et al.

We describe the JD Explore Academy's submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, including Chinese-English, German-English, Czech-English, Russian-English, and Japanese-English. We push the limit of our previous work -- bidirectional training for translation by scaling up two main factors, i.e. language pairs and model sizes, namely the \textbf{Vega-MT} system. As for language pairs, we scale the "bidirectional" up to the "multidirectional" settings, covering all participating languages, to exploit the common knowledge across languages, and transfer them to the downstream bilingual tasks. As for model sizes, we scale the Transformer-Big up to the extremely large model that owns nearly 4.7 Billion parameters, to fully enhance the model capacity for our Vega-MT. Also, we adopt the data augmentation strategies, e.g. cycle translation for monolingual data, and bidirectional self-training for bilingual and monolingual data, to comprehensively exploit the bilingual and monolingual data. To adapt our Vega-MT to the general domain test set, generalization tuning is designed. Based on the official automatic scores of constrained systems, in terms of the sacreBLEU shown in Figure-1, we got the 1st place on {Zh-En (33.5), En-Zh (49.7), De-En (33.7), En-De (37.8), Cs-En (54.9), En-Cs (41.4) and En-Ru (32.7)}, 2nd place on {Ru-En (45.1) and Ja-En (25.6)}, and 3rd place on {En-Ja(41.5)}, respectively; W.R.T the COMET, we got the 1st place on {Zh-En (45.1), En-Zh (61.7), De-En (58.0), En-De (63.2), Cs-En (74.7), Ru-En (64.9), En-Ru (69.6) and En-Ja (65.1)}, 2nd place on {En-Cs (95.3) and Ja-En (40.6)}, respectively.

Renjie Xu, Xinghao Yang, Baodi Liu et al.

Few-Shot classification aims at solving problems that only a few samples are available in the training process. Due to the lack of samples, researchers generally employ a set of training tasks from other domains to assist the target task, where the distribution between assistant tasks and the target task is usually different. To reduce the distribution gap, several lines of methods have been proposed, such as data augmentation and domain alignment. However, one common drawback of these algorithms is that they ignore the similarity task selection before training. The fundamental problem is to push the auxiliary tasks close to the target task. In this paper, we propose a novel task selecting algorithm, named Optimal Transport Task Selecting (OTTS), to construct a training set by selecting similar tasks for Few-Shot learning. Specifically, the OTTS measures the task similarity by calculating the optimal transport distance and completes the model training via a self-supervised strategy. By utilizing the selected tasks with OTTS, the training process of Few-Shot learning become more stable and effective. Other proposed methods including data augmentation and domain alignment can be used in the meantime with OTTS. We conduct extensive experiments on a variety of datasets, including MiniImageNet, CIFAR, CUB, Cars, and Places, to evaluate the effectiveness of OTTS. Experimental results validate that our OTTS outperforms the typical baselines, i.e., MAML, matchingnet, protonet, by a large margin (averagely 1.72\% accuracy improvement).

Jian Pang, Dacheng Zhang, Huafeng Li et al.

In a conventional domain adaptation person Re-identification (Re-ID) task, both the training and test images in target domain are collected under the sunny weather. However, in reality, the pedestrians to be retrieved may be obtained under severe weather conditions such as hazy, dusty and snowing, etc. This paper proposes a novel Interference Suppression Model (ISM) to deal with the interference caused by the hazy weather in domain adaptation person Re-ID. A teacherstudent model is used in the ISM to distill the interference information at the feature level by reducing the discrepancy between the clear and the hazy intrinsic similarity matrix. Furthermore, in the distribution level, the extra discriminator is introduced to assist the student model make the interference feature distribution more clear. The experimental results show that the proposed method achieves the superior performance on two synthetic datasets than the stateof-the-art methods. The related code will be released online https://github.com/pangjian123/ISM-ReID.

Xinghao Yang, Weifeng Liu, Shengli Zhang et al.

Real world traffic sign recognition is an important step towards building autonomous vehicles, most of which highly dependent on Deep Neural Networks (DNNs). Recent studies demonstrated that DNNs are surprisingly susceptible to adversarial examples. Many attack methods have been proposed to understand and generate adversarial examples, such as gradient based attack, score based attack, decision based attack, and transfer based attacks. However, most of these algorithms are ineffective in real-world road sign attack, because (1) iteratively learning perturbations for each frame is not realistic for a fast moving car and (2) most optimization algorithms traverse all pixels equally without considering their diverse contribution. To alleviate these problems, this paper proposes the targeted attention attack (TAA) method for real world road sign attack. Specifically, we have made the following contributions: (1) we leverage the soft attention map to highlight those important pixels and skip those zero-contributed areas - this also helps to generate natural perturbations, (2) we design an efficient universal attack that optimizes a single perturbation/noise based on a set of training images under the guidance of the pre-trained attention map, (3) we design a simple objective function that can be easily optimized, (4) we evaluate the effectiveness of TAA on real world data sets. Experimental results validate that the TAA method improves the attack successful rate (nearly 10%) and reduces the perturbation loss (about a quarter) compared with the popular RP2 method. Additionally, our TAA also provides good properties, e.g., transferability and generalization capability. We provide code and data to ensure the reproducibility: https://github.com/AdvAttack/RoadSignAttack.

Yangxu Yin, Honglong Chen, Yudong Gao et al.

Backdoor attacks pose a significant threat to deep neural networks, as backdoored models would misclassify poisoned samples with specific triggers into target classes while maintaining normal performance on clean samples. Among these, multi-target backdoor attacks can simultaneously target multiple classes. However, existing multi-target backdoor attacks all follow the dirty-label paradigm, where poisoned samples are mislabeled, and most of them require an extremely high poisoning rate. This makes them easily detectable by manual inspection. In contrast, clean-label attacks are more stealthy, as they avoid modifying the labels of poisoned samples. However, they generally struggle to achieve stable and satisfactory attack performance and often fail to scale effectively to multi-target attacks. To address this issue, we propose the Feature-based Full-target Clean-label Backdoor Attacks (FFCBA) which consists of two paradigms: Feature-Spanning Backdoor Attacks (FSBA) and Feature-Migrating Backdoor Attacks (FMBA). FSBA leverages class-conditional autoencoders to generate noise triggers that align perturbed in-class samples with the original category's features, ensuring the effectiveness, intra-class consistency, inter-class specificity and natural-feature correlation of triggers. While FSBA supports swift and efficient attacks, its cross-model attack capability is relatively weak. FMBA employs a two-stage class-conditional autoencoder training process that alternates between using out-of-class samples and in-class samples. This allows FMBA to generate triggers with strong target-class features, making it highly effective for cross-model attacks. We conduct experiments on multiple datasets and models, the results show that FFCBA achieves outstanding attack performance and maintains desirable robustness against the state-of-the-art backdoor defenses.

Yangxu Yin, Honglong Chen, Yudong Gao et al.

Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows attackers to control the model to misclassify poisoned samples with triggers into any desired target class during inference, exhibiting superior attack performance compared with conventional backdoor attacks. However, existing multi-target backdoor attacks fail to guarantee trigger specificity and stealthiness in black-box settings, resulting in two main issues. First, they are unable to simultaneously target all classes when only training data can be manipulated, limiting their effectiveness in realistic attack scenarios. Second, the triggers often lack visual imperceptibility, making poisoned samples easy to detect. To address these problems, we propose a Spatial-based Full-target Invisible Backdoor Attack, called SFIBA. It restricts triggers for different classes to specific local spatial regions and morphologies in the pixel space to ensure specificity, while employing a frequency-domain-based trigger injection method to guarantee stealthiness. Specifically, for injection of each trigger, we first apply fast fourier transform to obtain the amplitude spectrum of clean samples in local spatial regions. Then, we employ discrete wavelet transform to extract the features from the amplitude spectrum and use singular value decomposition to integrate the trigger. Subsequently, we selectively filter parts of the trigger in pixel space to implement trigger morphology constraints and adjust injection coefficients based on visual effects. We conduct experiments on multiple datasets and models. The results demonstrate that SFIBA can achieve excellent attack performance and stealthiness, while preserving the model's performance on benign samples, and can also bypass existing backdoor defenses.

Zhichen Ni, Honglong Chen, Zhe Li et al.

With the rapid development of Artificial Intelligence (AI) and Internet of Things (IoTs), an increasing number of computation intensive or delay sensitive biomedical data processing and analysis tasks are produced in vehicles, bringing more and more challenges to the biometric monitoring of drivers. Edge computing is a new paradigm to solve these challenges by offloading tasks from the resource-limited vehicles to Edge Servers (ESs) in Road Side Units (RSUs). However, most of the traditional offloading schedules for vehicular networks concentrate on the edge, while some tasks may be too complex for ESs to process. To this end, we consider a collaborative vehicular network in which the cloud, edge and terminal can cooperate with each other to accomplish the tasks. The vehicles can offload the computation intensive tasks to the cloud to save the resource of edge. We further construct the virtual resource pool which can integrate the resource of multiple ESs since some regions may be covered by multiple RSUs. In this paper, we propose a Multi-Scenario offloading schedule for biomedical data processing and analysis in Cloud-Edge-Terminal collaborative vehicular networks called MSCET. The parameters of the proposed MSCET are optimized to maximize the system utility. We also conduct extensive simulations to evaluate the proposed MSCET and the results illustrate that MSCET outperforms other existing schedules.

Shuai Shao, Lei Xing, Rui Xu et al.

In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). ii) Meta-test. Apply the trained FEM to the novel data (category is different from base data) to acquire the feature embeddings and recognize them. Although researchers have made remarkable breakthroughs in FSL, there still exists a fundamental problem. Since the trained FEM with base data usually cannot adapt to the novel class flawlessly, the novel data's feature may lead to the distribution shift problem. To address this challenge, we hypothesize that even if most of the decisions based on different FEMs are viewed as weak decisions, which are not available for all classes, they still perform decently in some specific categories. Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model. MDFM is a simple, flexible, non-parametric method that can directly apply to the existing FEMs. Besides, we extend the proposed MDFM to two FSL settings (i.e., supervised and semi-supervised settings). We evaluate the proposed method on five benchmark datasets and achieve significant improvements of 3.4%-7.3% compared with state-of-the-arts.

Xinghao Yang, Weifeng Liu, James Bailey et al.

Deep neural networks (DNNs) are known to be vulnerable to adversarial images, while their robustness in text classification is rarely studied. Several lines of text attack methods have been proposed in the literature, including character-level, word-level, and sentence-level attacks. However, it is still a challenge to minimize the number of word changes necessary to induce misclassification, while simultaneously ensuring lexical correctness, syntactic soundness, and semantic similarity. In this paper, we propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models. Our method has four major merits. Firstly, we propose to attack text documents not only at the unigram word level but also at the bigram level which better keeps semantics and avoids producing meaningless outputs. Secondly, we propose a hybrid method to replace the input words with options among both their synonyms candidates and sememe candidates, which greatly enriches the potential substitutions compared to only using synonyms. Thirdly, we design an optimization algorithm, i.e., Semantic Preservation Optimization (SPO), to determine the priority of word replacements, aiming to reduce the modification cost. Finally, we further improve the SPO with a semantic Filter (named SPOF) to find the adversarial example with the highest semantic similarity. We evaluate the effectiveness of our BU-SPO and BU-SPOF on IMDB, AG's News, and Yahoo! Answers text datasets by attacking four popular DNNs models. Results show that our methods achieve the highest attack success rates and semantics rates by changing the smallest number of words compared with existing methods.

Yibing Liu, Yangyang Guo, Jianhua Yin et al.

Visual attention in Visual Question Answering (VQA) targets at locating the right image regions regarding the answer prediction, offering a powerful technique to promote multi-modal understanding. However, recent studies have pointed out that the highlighted image regions from the visual attention are often irrelevant to the given question and answer, leading to model confusion for correct visual reasoning. To tackle this problem, existing methods mostly resort to aligning the visual attention weights with human attentions. Nevertheless, gathering such human data is laborious and expensive, making it burdensome to adapt well-developed models across datasets. To address this issue, in this paper, we devise a novel visual attention regularization approach, namely AttReg, for better visual grounding in VQA. Specifically, AttReg firstly identifies the image regions which are essential for question answering yet unexpectedly ignored (i.e., assigned with low attention weights) by the backbone model. And then a mask-guided learning scheme is leveraged to regularize the visual attention to focus more on these ignored key regions. The proposed method is very flexible and model-agnostic, which can be integrated into most visual attention-based VQA models and require no human attention supervision. Extensive experiments over three benchmark datasets, i.e., VQA-CP v2, VQA-CP v1, and VQA v2, have been conducted to evaluate the effectiveness of AttReg. As a by-product, when incorporating AttReg into the strong baseline LMH, our approach can achieve a new state-of-the-art accuracy of 60.00% with an absolute performance gain of 7.01% on the VQA-CP v2 benchmark dataset...

Shuai Shao, Rui Xu, Yan-Jiang Wang et al.

In recent years, the attention mechanism contributes significantly to hypergraph based neural networks. However, these methods update the attention weights with the network propagating. That is to say, this type of attention mechanism is only suitable for deep learning-based methods while not applicable to the traditional machine learning approaches. In this paper, we propose a hypergraph based sparse attention mechanism to tackle this issue and embed it into dictionary learning. More specifically, we first construct a sparse attention hypergraph, asset attention weights to samples by employing the $\ell_1$-norm sparse regularization to mine the high-order relationship among sample features. Then, we introduce the hypergraph Laplacian operator to preserve the local structure for subspace transformation in dictionary learning. Besides, we incorporate the discriminative information into the hypergraph as the guidance to aggregate samples. Unlike previous works, our method updates attention weights independently, does not rely on the deep network. We demonstrate the efficacy of our approach on four benchmark datasets.

Jinfeng Li, Weifeng Liu, Yicong Zhou et al.

Domain adaptation aims to generalize a model from a source domain to tackle tasks in a related but different target domain. Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain. However, these algorithms will be infeasible when only a few labeled data exist in the source domain, and thus the performance decreases significantly. To address this challenge, we propose a Domain-invariant Graph Learning (DGL) approach for domain adaptation with only a few labeled source samples. Firstly, DGL introduces the Nystrom method to construct a plastic graph that shares similar geometric property as the target domain. And then, DGL flexibly employs the Nystrom approximation error to measure the divergence between plastic graph and source graph to formalize the distribution mismatch from the geometric perspective. Through minimizing the approximation error, DGL learns a domain-invariant geometric graph to bridge source and target domains. Finally, we integrate the learned domain-invariant graph with the semi-supervised learning and further propose an adaptive semi-supervised model to handle the cross-domain problems. The results of extensive experiments on popular datasets verify the superiority of DGL, especially when only a few labeled source samples are available.

Xin Xu, Lei Liu, Weifeng Liu et al.

Annotating a large-scale image dataset is very tedious, yet necessary for training person re-identification models. To alleviate such a problem, we present an active hard sample mining framework via training an effective re-ID model with the least labeling efforts. Considering that hard samples can provide informative patterns, we first formulate an uncertainty estimation to actively select hard samples to iteratively train a re-ID model from scratch. Then, intra-diversity estimation is designed to reduce the redundant hard samples by maximizing their diversity. Moreover, we propose a computer-assisted identity recommendation module embedded in the active hard sample mining framework to help human annotators to rapidly and accurately label the selected samples. Extensive experiments were carried out to demonstrate the effectiveness of our method on several public datasets. Experimental results indicate that our method can reduce 57%, 63%, and 49% annotation efforts on the Market1501, MSMT17, and CUHK03, respectively, while maximizing the performance of the re-ID model.

Yan-Jiang Wang, Shuai Shao, Rui Xu et al.

Dictionary learning methods can be split into: i) class specific dictionary learning ii) class shared dictionary learning. The difference between the two categories is how to use discriminative information. With the first category, samples of different classes are mapped into different subspaces, which leads to some redundancy with the class specific base vectors. While for the second category, the samples in each specific class can not be described accurately. In this paper, we first propose a novel class shared dictionary learning method named label embedded dictionary learning (LEDL). It is the improvement based on LCKSVD, which is easier to find out the optimal solution. Then we propose a novel framework named cascaded dictionary learning framework (CDLF) to combine the specific dictionary learning with shared dictionary learning to describe the feature to boost the performance of classification sufficiently. Extensive experimental results on six benchmark datasets illustrate that our methods are capable of achieving superior performance compared to several state-of-art classification algorithms.

Shuai Shao, Yan-Jiang Wang, Bao-Di Liu et al.

Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification. The objective function of LC-KSVD is consisted of reconstruction error, classification error and discriminative sparse codes error with L0-norm sparse regularization term. The L0-norm, however, leads to NP-hard problem. Despite some methods such as orthogonal matching pursuit can help solve this problem to some extent, it is quite difficult to find the optimum sparse solution. To overcome this limitation, we propose a label embedded dictionary learning (LEDL) method to utilise the L1-norm as the sparse regularization term so that we can avoid the hard-to-optimize problem by solving the convex optimization problem. Alternating direction method of multipliers and blockwise coordinate descent algorithm are then exploited to optimize the corresponding objective function. Extensive experimental results on six benchmark datasets illustrate that the proposed algorithm has achieved superior performance compared to some conventional classification algorithms.

Xueqi Ma, Weifeng Liu, Dapeng Tao et al.

Recently, manifold regularized semi-supervised learning (MRSSL) received considerable attention because it successfully exploits the geometry of the intrinsic data probability distribution including both labeled and unlabeled samples to leverage the performance of a learning model. As a natural nonlinear generalization of graph Laplacian, p-Laplacian has been proved having the rich theoretical foundations to better preserve the local structure. However, it is difficult to determine the fitting graph p-Lapalcian i.e. the parameter which is a critical factor for the performance of graph p-Laplacian. Therefore, we develop an ensemble p-Laplacian regularization (EpLapR) to fully approximate the intrinsic manifold of the data distribution. EpLapR incorporates multiple graphs into a regularization term in order to sufficiently explore the complementation of graph p-Laplacian. Specifically, we construct a fused graph by introducing an optimization approach to assign suitable weights on different p-value graphs. And then, we conduct semi-supervised learning framework on the fused graph. Extensive experiments on UC-Merced data set demonstrate the effectiveness and efficiency of the proposed method.

Yanan Guo, Lei Li, Weifeng Liu et al.

The ever-growing popularity of Kinect and inertial sensors has prompted intensive research efforts on human action recognition. Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition. In this paper, we propose a new unsupervised feature fusion method termed Multiview Cauchy Estimator Feature Embedding (MCEFE) for human action recognition. By minimizing empirical risk, MCEFE integrates the encoded complementary information in multiple views to find the unified data representation and the projection matrices. To enhance robustness to outliers, the Cauchy estimator is imposed on the reconstruction error. Furthermore, ensemble manifold regularization is enforced on the projection matrices to encode the correlations between different views and avoid overfitting. Experiments are conducted on the new Chinese Academy of Sciences - Yunnan University - Multimodal Human Action Database (CAS-YNU-MHAD) to demonstrate the effectiveness and robustness of MCEFE for human action recognition.

Hongli Liu, Weifeng Liu, Yanjiang Wang

Facial analysis has attracted much attention in the technology for human-machine interface. Different methods of classification based on sparse representation and Gabor kernels have been widely applied in the fields of facial analysis. However, most of these methods treat face from a whole view standpoint. In terms of the importance of different facial views, in this paper, we present multi-view face analysis based on sparse representation and Gabor wavelet coefficients. To evaluate the performance, we conduct face analysis experiments including face recognition (FR) and face expression recognition (FER) on JAFFE database. Experiments are conducted from two parts: (1) Face images are divided into three facial parts which are forehead, eye and mouth. (2) Face images are divided into 8 parts by the orientation of Gabor kernels. Experimental results demonstrate that the proposed methods can significantly boost the performance and perform better than the other methods.

Weifeng Liu, Dacheng Tao, Jun Cheng et al.

Sparse coding represents a signal sparsely by using an overcomplete dictionary, and obtains promising performance in practical computer vision applications, especially for signal restoration tasks such as image denoising and image inpainting. In recent years, many discriminative sparse coding algorithms have been developed for classification problems, but they cannot naturally handle visual data represented by multiview features. In addition, existing sparse coding algorithms use graph Laplacian to model the local geometry of the data distribution. It has been identified that Laplacian regularization biases the solution towards a constant function which possibly leads to poor extrapolating power. In this paper, we present multiview Hessian discriminative sparse coding (mHDSC) which seamlessly integrates Hessian regularization with discriminative sparse coding for multiview learning problems. In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation. We conduct extensive experiments on PASCAL VOC'07 dataset and demonstrate the effectiveness of mHDSC for image annotation.