Lu Zhang

Linfeng Liu, Siyu Liu, Lu Zhang et al.

Accurate medical classification requires a large number of multi-modal data, and in many cases, different feature types. Previous studies have shown promising results when using multi-modal data, outperforming single-modality models when classifying diseases such as Alzheimer's Disease (AD). However, those models are usually not flexible enough to handle missing modalities. Currently, the most common workaround is discarding samples with missing modalities which leads to considerable data under-utilization. Adding to the fact that labeled medical images are already scarce, the performance of data-driven methods like deep learning can be severely hampered. Therefore, a multi-modal method that can handle missing data in various clinical settings is highly desirable. In this paper, we present Multi-Modal Mixing Transformer (3MAT), a disease classification transformer that not only leverages multi-modal data but also handles missing data scenarios. In this work, we test 3MT for AD and Cognitively normal (CN) classification and mild cognitive impairment (MCI) conversion prediction to progressive MCI (pMCI) or stable MCI (sMCI) using clinical and neuroimaging data. The model uses a novel Cascaded Modality Transformer architecture with cross-attention to incorporate multi-modal information for more informed predictions. We propose a novel modality dropout mechanism to ensure an unprecedented level of modality independence and robustness to handle missing data scenarios. The result is a versatile network that enables the mixing of arbitrary numbers of modalities with different feature types and also ensures full data utilization missing data scenarios. The model is trained and evaluated on the ADNI dataset with the SOTRA performance and further evaluated with the AIBL dataset with missing data.

Yuzhong Chen, Yu Du, Zhenxiang Xiao et al.

Vision transformer (ViT) and its variants have achieved remarkable successes in various visual tasks. The key characteristic of these ViT models is to adopt different aggregation strategies of spatial patch information within the artificial neural networks (ANNs). However, there is still a key lack of unified representation of different ViT architectures for systematic understanding and assessment of model representation performance. Moreover, how those well-performing ViT ANNs are similar to real biological neural networks (BNNs) is largely unexplored. To answer these fundamental questions, we, for the first time, propose a unified and biologically-plausible relational graph representation of ViT models. Specifically, the proposed relational graph representation consists of two key sub-graphs: aggregation graph and affine graph. The former one considers ViT tokens as nodes and describes their spatial interaction, while the latter one regards network channels as nodes and reflects the information communication between channels. Using this unified relational graph representation, we found that: a) a sweet spot of the aggregation graph leads to ViTs with significantly improved predictive performance; b) the graph measures of clustering coefficient and average path length are two effective indicators of model prediction performance, especially when applying on the datasets with small samples; c) our findings are consistent across various ViT architectures and multiple datasets; d) the proposed relational graph representation of ViT has high similarity with real BNNs derived from brain science data. Overall, our work provides a novel unified and biologically-plausible paradigm for more interpretable and effective representation of ViT ANNs.

Shijie Chang, Zeqi Hao, Ben Kang et al.

In this paper, we introduce 3rd place solution for PVUW2023 VSS track. Semantic segmentation is a fundamental task in computer vision with numerous real-world applications. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation. Through our experimentation, we find that InternImage-H as the backbone and Mask2former as the segmentation head achieves the best performance. In addition, we explore two post-precessing methods: CascadePSP and Segment Anything Model (SAM). Ultimately, our approach obtains 62.60\% and 64.84\% mIoU on the VSPW test set1 and final test set, respectively, securing the third position in the PVUW2023 VSS track.

Jin Huang, Lu Zhang, Yongshun Gong et al.

Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos. While a great progress has been observed, most of the existing SPS approaches concentrate solely on extracting features from the original image, neglecting that multiple views, e.g, saturation level, color histogram and depth of field of the image, will be of benefit to successfully reflecting the subtle aesthetic changes. Taken multi-view into consideration, we leverage a graph neural network to construct the relationships between multi-view features. Besides, multiple views are aggregated with an adaptive-weight self-attention module to verify the significance of each view. Finally, a siamese network is proposed to select the best one from a series of nearly identical photos. Experimental results demonstrate that our model accomplish the highest success rates compared with competitive methods.

Heng Huang, Lin Zhao, Xintao Hu et al.

Visual attention is a fundamental mechanism in the human brain, and it inspires the design of attention mechanisms in deep neural networks. However, most of the visual attention studies adopted eye-tracking data rather than the direct measurement of brain activity to characterize human visual attention. In addition, the adversarial relationship between the attention-related objects and attention-neglected background in the human visual system was not fully exploited. To bridge these gaps, we propose a novel brain-inspired adversarial visual attention network (BI-AVAN) to characterize human visual attention directly from functional brain activity. Our BI-AVAN model imitates the biased competition process between attention-related/neglected objects to identify and locate the visual objects in a movie frame the human brain focuses on in an unsupervised manner. We use independent eye-tracking data as ground truth for validation and experimental results show that our model achieves robust and promising results when inferring meaningful human visual attention and mapping the relationship between brain activities and visual stimuli. Our BI-AVAN model contributes to the emerging field of leveraging the brain's functional architecture to inspire and guide the model design in artificial intelligence (AI), e.g., deep neural networks.

Qiulin Wang, Lu Zhang, Bo Li

Recent success of generative adversarial networks (GAN) has made great progress on the face animation task. However, the complex scene structure of a face image still makes it a challenge to generate videos with face poses significantly deviating from the source image. On one hand, without knowing the facial geometric structure, generated face images might be improperly distorted. On the other hand, some area of the generated image might be occluded in the source image, which makes it difficult for GAN to generate realistic appearance. To address these problems, we propose a structure aware face animation (SAFA) method which constructs specific geometric structures to model different components of a face image. Following the well recognized motion based face animation technique, we use a 3D morphable model (3DMM) to model the face, multiple affine transforms to model the other foreground components like hair and beard, and an identity transform to model the background. The 3DMM geometric embedding not only helps generate realistic structure for the driving scene, but also contributes to better perception of occluded area in the generated image. Besides, we further propose to exploit the widely studied inpainting technique to faithfully recover the occluded image area. Both quantitative and qualitative experiment results have shown the superiority of our method. Code is available at https://github.com/Qiulin-W/SAFA.

Yi Zhang, Geng Chen, Qian Chen et al.

We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms. Our SA-Net exploits the rich information of focal stacks via 3D convolutional neural networks, decodes the high-level features of multi-modal light field data with two cascaded synergistic attention modules, and predicts the saliency map using an effective feature fusion module in a progressive manner. Extensive experiments on three widely-used benchmark datasets show that our SA-Net outperforms 28 state-of-the-art models, sufficiently demonstrating its effectiveness and superiority. Our code is available at https://github.com/PanoAsh/SA-Net.

Yi Zhang, Lu Zhang, Wassim Hamidouche et al.

Fixation prediction (FP) in panoramic contents has been widely investigated along with the booming trend of virtual reality (VR) applications. However, another issue within the field of visual saliency, salient object detection (SOD), has been seldom explored in 360° (or omnidirectional) images due to the lack of datasets representative of real scenes with pixel-level annotations. Toward this end, we collect 107 equirectangular panoramas with challenging scenes and multiple object classes. Based on the consistency between FP and explicit saliency judgements, we further manually annotate 1,165 salient objects over the collected images with precise masks under the guidance of real human eye fixation maps. Six state-of-the-art SOD models are then benchmarked on the proposed fixation-based 360° image dataset (F-360iSOD), by applying a multiple cubic projection-based fine-tuning method. Experimental results show a limitation of the current methods when used for SOD in panoramic images, which indicates the proposed dataset is challenging. Key issues for 360° SOD is also discussed. The proposed dataset is available at https://github.com/PanoAsh/F-360iSOD.

Jing Zhang, Xiaowei Yu, Tong Chen et al.

The Lewy body dementia (LBD) is the second most common neurodegenerative dementia after Alzheimer's disease (AD). Early differentiation between AD and LBD is crucial because they require different treatment approaches, but this is challenging due to significant clinical overlap, heterogeneity, complex pathogenesis, and the rarity of LBD. While recent advances in artificial intelligence (AI) demonstrate powerful learning capabilities and offer new hope for accurate diagnosis, existing methods primarily focus on designing "neural-level networks". Our work represents a pioneering effort in modeling system-level artificial neural network called BrainNet-MoE for brain modeling and diagnosing. Inspired by the brain's hierarchical organization of bottom-up sensory integration and top-down control, we design a set of disease-specific expert groups to process brain sub-network under different condition, A disease gate mechanism guides the specializa-tion of expert groups, while a transformer layer enables communication be-tween all sub-networks, generating a comprehensive whole-brain represen-tation for downstream disease classification. Experimental results show superior classification accuracy with interpretable insights into how brain sub-networks contribute to different neurodegenerative conditions.

Lu Zhang, Sangarapillai Lambotharan, Gan Zheng et al.

Advantages of deep learning over traditional methods have been demonstrated for radio signal classification in the recent years. However, various researchers have discovered that even a small but intentional feature perturbation known as adversarial examples can significantly deteriorate the performance of the deep learning based radio signal classification. Among various kinds of adversarial examples, universal adversarial perturbation has gained considerable attention due to its feature of being data independent, hence as a practical strategy to fool the radio signal classification with a high success rate. Therefore, in this paper, we investigate a defense system called neural rejection system to propose against universal adversarial perturbations, and evaluate its performance by generating white-box universal adversarial perturbations. We show that the proposed neural rejection system is able to defend universal adversarial perturbations with significantly higher accuracy than the undefended deep neural network.

Hongxu Wang, Zhu Sun, Yingpeng Du et al.

Recommender systems (RSs) play a crucial role in shaping our digital interactions, influencing how we access and engage with information across various domains. Traditional research has predominantly centered on maximizing recommendation accuracy, often leading to unintended side effects such as echo chambers and constrained user experiences. Drawing inspiration from autonomous driving, we introduce a novel framework that categorizes RS autonomy into five distinct levels, ranging from basic rule-based accuracy-driven systems to behavior-aware, uncertain multi-objective RSs - where users may have varying needs, such as accuracy, diversity, and fairness. In response, we propose an approach that dynamically identifies and optimizes multiple objectives based on individual user preferences, fostering more ethical and intelligent user-centric recommendations. To navigate the uncertainty inherent in multi-objective RSs, we develop a Bayesian optimization (BO) framework that captures personalized trade-offs between different objectives while accounting for their uncertain interdependencies. Furthermore, we introduce an orthogonal meta-learning paradigm to enhance BO efficiency and effectiveness by leveraging shared knowledge across similar tasks and mitigating conflicts among objectives through the discovery of orthogonal information. Finally, extensive empirical evaluations demonstrate the effectiveness of our method in optimizing uncertain multi-objectives for individual users, paving the way for more adaptive and user-focused RSs.

Ziqing Wu, Zhu Sun, Dongxia Wang et al.

Large language models (LLMs) have shown promising potential for next Point-of-Interest (POI) recommendation. However, existing methods only perform direct zero-shot prompting, leading to ineffective extraction of user preferences, insufficient injection of collaborative signals, and a lack of user privacy protection. As such, we propose a novel Multitask Reflective Large Language Model for Privacy-preserving Next POI Recommendation (MRP-LLM), aiming to exploit LLMs for better next POI recommendation while preserving user privacy. Specifically, the Multitask Reflective Preference Extraction Module first utilizes LLMs to distill each user's fine-grained (i.e., categorical, temporal, and spatial) preferences into a knowledge base (KB). The Neighbor Preference Retrieval Module retrieves and summarizes the preferences of similar users from the KB to obtain collaborative signals. Subsequently, aggregating the user's preferences with those of similar users, the Multitask Next POI Recommendation Module generates the next POI recommendations via multitask prompting. Meanwhile, during data collection, a Privacy Transmission Module is specifically devised to preserve sensitive POI data. Extensive experiments on three real-world datasets demonstrate the efficacy of our proposed MRP-LLM in providing more accurate next POI recommendations with user privacy preserved.

Yue Wang, Xu Jia, Lu Zhang et al.

RGB-D saliency detection integrates information from both RGB images and depth maps to improve prediction of salient regions under challenging conditions. The key to RGB-D saliency detection is to fully mine and fuse information at multiple scales across the two modalities. Previous approaches tend to apply the multi-scale and multi-modal fusion separately via local operations, which fails to capture long-range dependencies. Here we propose a transformer-based network to address this issue. Our proposed architecture is composed of two modules: a transformer-based within-modality feature enhancement module (TWFEM) and a transformer-based feature fusion module (TFFM). TFFM conducts a sufficient feature fusion by integrating features from multiple scales and two modalities over all positions simultaneously. TWFEM enhances feature on each scale by selecting and integrating complementary information from other scales within the same modality before TFFM. We show that transformer is a uniform operation which presents great efficacy in both feature fusion and feature enhancement, and simplifies the model design. Extensive experimental results on six benchmark datasets demonstrate that our proposed network performs favorably against state-of-the-art RGB-D saliency detection methods.

Yi Zhang, Lu Zhang, Wassim Hamidouche et al.

In the past few years, numerous deep learning methods have been proposed to address the task of segmenting salient objects from RGB images. However, these approaches depending on single modality fail to achieve the state-of-the-art performance on widely used light field salient object detection (SOD) datasets, which collect large-scale natural images and provide multiple modalities such as multi-view, micro-lens images and depth maps. Most recently proposed light field SOD methods have acquired improving detecting accuracy, yet still predict rough objects' structures and perform slow inference speed. To this end, we propose CMA-Net, which consists of two novel cascaded mutual attention modules aiming at fusing the high level features from the modalities of all-in-focus and depth. Our proposed CMA-Net outperforms 30 SOD methods on two widely applied light field benchmark datasets. Besides, the proposed CMA-Net is able to inference at the speed of 53 fps. Extensive quantitative and qualitative experiments illustrate both the effectiveness and efficiency of our CMA-Net.

Yue Wang, Yuke Li, James H. Elder et al.

Depth information available from an RGB-D camera can be useful in segmenting salient objects when figure/ground cues from RGB channels are weak. This has motivated the development of several RGB-D saliency datasets and algorithms that use all four channels of the RGB-D data for both training and inference. Unfortunately, existing RGB-D saliency datasets are small, which may lead to overfitting and limited generalization for diverse scenarios. Here we propose a semi-supervised system for RGB-D saliency detection that can be trained on smaller RGB-D saliency datasets without saliency ground truth, while also make effective joint use of a large RGB saliency dataset with saliency ground truth together. To generalize our method on RGB-D saliency datasets, a novel prediction-guided cross-refinement module which jointly estimates both saliency and depth by mutual refinement between two respective tasks, and an adversarial learning approach are employed. Critically, our system does not require saliency ground-truth for the RGB-D datasets, which saves the massive human labor for hand labeling, and does not require the depth data for inference, allowing the method to be used for the much broader range of applications where only RGB data are available. Evaluation on seven RGB-D datasets demonstrates that even without saliency ground truth for RGB-D datasets and using only the RGB data of RGB-D datasets at inference, our semi-supervised system performs favorable against state-of-the-art fully-supervised RGB-D saliency detection methods that use saliency ground truth for RGB-D datasets at training and depth data at inference on two largest testing datasets. Our approach also achieves comparable results on other popular RGB-D saliency benchmarks.

Lu Zhang, Jian Zhang, Zhibin Li et al.

Inspired by the fact that spreading and collecting information through the Internet becomes the norm, more and more people choose to post for-profit contents (images and texts) in social networks. Due to the difficulty of network censors, malicious marketing may be capable of harming society. Therefore, it is meaningful to detect marketing intentions online automatically. However, gaps between multimodal data make it difficult to fuse images and texts for content marketing detection. To this end, this paper proposes Two-Branch Collaborative Graph Neural Networks to collaboratively represent multimodal data by Graph Convolution Networks (GCNs) in an end-to-end fashion. Experimental results demonstrate that our proposed method achieves superior graph classification performance for marketing intention detection.