Multi-modality fusion is the guarantee of the stability of autonomous driving systems. In this paper, we propose a general multi-modality cascaded fusion framework, exploiting the advantages of decision-level and feature-level fusion, utilizing target position, size, velocity, appearance and confidence to achieve accurate fusion results. In the fusion process, dynamic coordinate alignment(DCA) is conducted to reduce the error between sensors from different modalities. In addition, the calculation of affinity matrix is the core module of sensor fusion, we propose an affinity loss that improves the performance of deep affinity network(DAN). Last, the proposed step-by-step cascaded fusion framework is more interpretable and flexible compared to the end-toend fusion methods. Extensive experiments on Nuscenes [2] dataset show that our approach achieves the state-of-theart performance.dataset show that our approach achieves the state-of-the-art performance.
Integrating LiDAR and Camera information into Bird's-Eye-View (BEV) has become an essential topic for 3D object detection in autonomous driving. Existing methods mostly adopt an independent dual-branch framework to generate LiDAR and camera BEV, then perform an adaptive modality fusion. Since point clouds provide more accurate localization and geometry information, they could serve as a reliable spatial prior to acquiring relevant semantic information from the images. Therefore, we design a LiDAR-Guided View Transformer (LGVT) to effectively obtain the camera representation in BEV space and th…
Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Artificial Intelligence Research, Chinese Academy of Sciences（中国科学院人工智能研究院）；University of Chinese Academy of Sciences（中国科学院大学）
In this work, we address the task of referring image segmentation (RIS), which aims at predicting a segmentation mask for the object described by a natural language expression. Most existing methods focus on establishing unidirectional or directional relationships between visual and linguistic features to associate two modalities together, while the multi-scale context is ignored or insufficiently modeled. Multi-scale context is crucial to localize and segment those objects that have large scale variations during the multi-modal fusion process. To solve this problem, we propose a simple yet ef…
Huazhong University of Science and Technology（华中科技大学）
Semantic scene completion (SSC) aims to complete a partial 3D scene and predict its semantics simultaneously. Most existing works adopt the voxel representations, thus suffering from the growth of memory and computation cost as the voxel resolution increases. Though a few works attempt to solve SSC from the perspective of 3D point clouds, they have not fully exploited the correlation and complementarity between the two tasks of scene completion and semantic segmentation. In our work, we present CasFusionNet, a novel cascaded network for point cloud semantic scene completion by dense feature fu…
IBM Tokyo Laboratory（IBM东京实验室）；IBM Research - Tokyo（IBM东京研究院）
Lung nodule classification is a class imbalanced problem, as nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We showed that cascaded convolutional neural networks can classify the nodule candidates precisely for a class imbalanced nodule candidate data set in our previous study. In this paper, we propose Fusion classifier in conjunction with the cascaded convolutional neural network models. To fuse the models, nodule probabilities are calculated by…
Recent learning-based image fusion methods have marked numerous progress in pre-registered multi-modality data, but suffered serious ghosts dealing with misaligned multi-modality data, due to the spatial deformation and the difficulty narrowing cross-modality discrepancy. To overcome the obstacles, in this paper, we present a robust cross-modality generation-registration paradigm for unsupervised misaligned infrared and visible image fusion (IVIF). Specifically, we propose a Cross-modality Perceptual Style Transfer Network (CPSTN) to generate a pseudo infrared image taking a visible image as i…
Kunming University of Science and Technology（昆明理工大学）
Multispectral pedestrian detection is a technology designed to detect and locate pedestrians in Color and Thermal images, which has been widely used in automatic driving, video surveillance, etc. So far most available multispectral pedestrian detection algorithms only achieved limited success in pedestrian detection because of the lacking take into account the confusion of pedestrian information and background noise in Color and Thermal images. Here we propose a multispectral pedestrian detection algorithm, which mainly consists of a cascaded information enhancement module and a cross-modal at…
Shanghai Jiao Tong University（上海交通大学）；Shandong Cancer Hospital Affiliated to Shandong University（山东大学附属山东省肿瘤医院）；Deepwise AI Lab（深睿医疗人工智能实验室）
Segmentation of nasopharyngeal carcinoma (NPC) from Magnetic Resonance Images (MRI) is a crucial prerequisite for NPC radiotherapy. However, manually segmenting of NPC is time-consuming and labor-intensive. Additionally, single-modality MRI generally cannot provide enough information for its accurate delineation. Therefore, a multi-modality MRI fusion network (MMFNet) based on three modalities of MRI (T1, T2 and contrast-enhanced T1) is proposed to complete accurate segmentation of NPC. The backbone of MMFNet is designed as a multi-encoder-based network, consisting of several encoders to captu…
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
Xi’an Jiaotong University（西安交通大学）；ETH Zürich（苏黎世联邦理工学院）；Northwestern Polytechnical University（西北工业大学）；Research and Development Institute of Northwestern Polytechnical University in Shenzhen（西北工业大学深圳研究院）；Harvard University（哈佛大学）；University of Würzburg（维尔茨堡大学）
Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University（教育区块链与智能技术重点实验室，教育部，广西师范大学）；Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University（多源信息挖掘与安全广西重点实验室，广西师范大学）
MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality Adapters
School of Information and Electronics, Beijing Institute of Technology（信息与电子学院，北京理工大学）；Beijing Institute of Technology Chongqing Innovation Center（北京理工大学重庆创新中心）；National Key Laboratory for Space-Born Intelligent Information Processing（空间智能信息处理国家级重点实验室）；School of Automation, Beijing Institute of Technology（自动化学院，北京理工大学）
RGB-infrared person re-identification is a challenging task due to the intra-class variations and cross-modality discrepancy. Existing works mainly focus on learning modality-shared global representations by aligning image styles or feature distributions across modalities, while local feature from body part and relationships between person images are largely neglected. In this paper, we propose a Dual-level (i.e., local and global) Feature Fusion (DF^2) module by learning attention for discriminative feature from local to global manner. In particular, the attention for a local feature is deter…
Supervise-assisted Multi-modality Fusion Diffusion Model for PET Restoration
Beijing Institute of Technology（北京理工大学）；Research and Development Center of Agricultural Bank of China（中国农业银行研发中心）；Peking University（北京大学）；Beijing Normal University（北京师范大学）
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
Xi’an Jiaotong University（西安交通大学）；Computer Vision Lab, ETH Zürich（苏黎世联邦理工学院计算机视觉实验室）；Northwestern Polytechnical University（西北工业大学）；Macau University of Science and Technology（澳门科技大学）；University of Würzburg（维尔茨堡大学）
Scene depth information can help visual information for more accurate semantic segmentation. However, how to effectively integrate multi-modality information into representative features is still an open problem. Most of the existing work uses DCNNs to implicitly fuse multi-modality information. But as the network deepens, some critical distinguishing features may be lost, which reduces the segmentation performance. This work proposes a unified and efficient feature selectionand-fusion network (FSFNet), which contains a symmetric cross-modality residual fusion module used for explicit fusion o…
Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations
Academy for Engineering and Technology, Fudan University（复旦大学工程技术研究院）；Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；University of South Carolina（南卡罗来纳大学）
Heudiasyc（Heudiasyc实验室）；CNRS（法国国家科学研究中心）；Université de technologie de Compiègne（贡比涅技术大学）；Quantif（Quantif团队）；LITIS（LITIS实验室）；University of Rouen Normandy（鲁昂诺曼底大学）；Institut universitaire de France（法国大学研究院）；Henri Becquerel Cancer Center（亨利·贝克勒尔癌症中心）
As information sources are usually imperfect, it is necessary to take into account their reliability in multi-source information fusion tasks. In this paper, we propose a new deep framework allowing us to merge multi-MR image segmentation results using the formalism of Dempster-Shafer theory while taking into account the reliability of different modalities relative to different classes. The framework is composed of an encoder-decoder feature extraction module, an evidential segmentation module that computes a belief function at each voxel for each modality, and a multi-modality evidence fusion…
University of Sydney（悉尼大学）；Royal Prince Alfred Hospital（阿尔弗雷德王子医院）
The analysis of multi-modality positron emission tomography and computed tomography (PET-CT) images for computer aided diagnosis applications requires combining the sensitivity of PET to detect abnormal regions with anatomical localization from CT. Current methods for PET-CT image analysis either process the modalities separately or fuse information from each modality based on knowledge about the image analysis task. These methods generally do not consider the spatially varying visual characteristics that encode different information across the different modalities, which have different priori…
When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation
Central China Normal University（华中师范大学）；Huazhong University of Science and Technology（华中科技大学）；Guangzhou University of Chinese Medicine（广州中医药大学）；The First Affiliated Hospital of Guangzhou University of Chinese Medicine（广州中医药大学第一附属医院）；University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）
Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation
Engineering Research Center of Learning-Based Intelligent System (Ministry of Education)（基于学习的智能系统工程研究中心（教育部））；Key Laboratory of Computer Vision（计算机视觉重点实验室）；Tianjin Key Laboratory of Civil Structure Protection（天津建筑物结构保护重点实验室）；Tianjin Chengjian University（天津城建大学）
HyPCA-Net: Advancing Multimodal Fusion in Medical Image Analysis
Indian Institute of Technology Ropar（印度理工学院罗帕尔分校）；RoentGen Health（RoentGen健康公司）；Lulea University of Technology（卢勒奥大学）；QUT（昆士兰科技大学）；RMIT University（皇家墨尔本理工大学）；Curtin University（Curtin大学）；Deakin University（德肯大学）
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-atten…
School of Electronics and Information Technology, Sun Yat-sen University（中山大学电子与信息工程学院）
Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this paper, we propose a novel adversarial encoder-decoder-classifier framework to learn a modality-invariant embedding space. Since the distributions of various modalities vary in nature, to reduce the modality gap, we translate the distributions of source modalities into that of target modality via their respective encoders using adversarial training. Furthermore…
The Chinese University of Hong Kong（香港中文大学）；Imperial College Longdon（伦敦帝国理工学院）；Imsight Medical Technology Co. Ltd.（艾迈医疗科技有限公司）；The Hong Kong Polytechnic University（香港理工大学）；Chinese Academy of Sciences（中国科学院）
Accurate medical image segmentation commonly requires effective learning of the complementary information from multimodal data. However, in clinical practice, we often encounter the problem of missing imaging modalities. We tackle this challenge and propose a novel multimodal segmentation framework which is robust to the absence of imaging modalities. Our network uses feature disentanglement to decompose the input modalities into the modality-specific appearance code, which uniquely sticks to each modality, and the modality-invariant content code, which absorbs multimodal information for the s…
Beijing Institution of Technology（北京理工大学）；Baidu Inc.（百度公司）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Answering semantically-complicated questions according to an image is challenging in Visual Question Answering (VQA) task. Although the image can be well represented by deep learning, the question is always simply embedded and cannot well indicate its meaning. Besides, the visual and textual features have a gap for different modalities, it is difficult to align and utilize the cross-modality information. In this paper, we focus on these two problems and propose a Graph Matching Attention (GMA) network. Firstly, it not only builds graph for the image, but also constructs graph for the question …
Boosting Multimodal Learning via Disentangled Gradient Learning
The Laboratory of Intelligent Collaborative Computing of UESTC（UESTC智能协同计算实验室）；The School of Information and Communication Engineering of UESTC（UESTC信息与通信工程学院）
Fuzhou University（福州大学）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；King’s College London（伦敦国王学院）
Both image registration and label fusion in the multi-atlas segmentation (MAS) rely on the intensity similarity between target and atlas images. However, such similarity can be problematic when target and atlas images are acquired using different imaging protocols. High-level structure information can provide reliable similarity measurement for cross-modality images when cooperating with deep neural networks (DNNs). This work presents a new MAS framework for cross-modality images, where both image registration and label fusion are achieved by DNNs. For image registration, we propose a consiste…
