Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Department of Physics, J.K. Institute of Science（J.K.科学研究所物理系）；World Scientific University（世界科学出版社大学）；University of Intelligent Studies（智能研究大学）；School of Computer and Electronic Information, Nanjing Normal University（南京师范大学计算机与电子信息学院）
Jun Li, Yingying Shi, Zhixuan Ruan, Nan Guo, Jianhua Xu
In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate detection. Although current Mamba-based methods can efficiently model long-range dependencies, they still struggle to capture small objects with abundant local details, which hinders joint modeling of local structures and global semantics. Moreover, state-space models exhibit limited hierarchical feature representation and weak cross-scale interaction due to flat sequential modeling and insufficient spatial inductive biases, leading to sub-optimal performance in complex scenes. To address these issues, we propose a Mamba with Deformable Dilated Convolutions Network (MDDCNet) for accurate traffic object detection in this study. In MDDCNet, a well-designed hybrid backbone with successive Multi-Scale Deformable Dilated Convolution (MSDDC) blocks and Mamba blocks enables hierarchical feature representation from local details to global semantics. Meanwhile, a Channel-Enhanced Feed-Forward Network (CE-FFN) is further devised to overcome the limited channel interaction capability of conventional feed-forward networks, whilst a Mamba-based Attention-Aggregating Feature Pyramid Network (A^2FPN) is constructed to achieve enhanced multi-scale feature fusion and interaction. Extensive experimental results on public benchmark and real-world datasets demonstrate the superiority of our method over various advanced detectors. The code is available at https://github.com/Bettermea/MDDCNet.
DC-Mamba: Bi-temporal deformable alignment and scale-sparse enhancement for remote sensing change detection
Min Sun School of Materials Science and Engineering Hainan University（孙敏 海南大学材料科学与工程学院）；Fenghui Guo School of Materials Science and Engineering Hainan University（郭峰 海南大学材料科学与工程学院）
MambaDSF: Multi-Scale SSM with Dilated Feature Fusion for Sonar Small Target Detection
School of Information Science and Engineering, Ocean University of China（中国海洋大学信息科学与工程学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection
College of Mechanical and Vehicle Engineering, Hunan University（湖南大学机械与车辆工程学院）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration
Image Processing Center, Beihang University, Beijing, China（北京航空航天大学图像处理中心）；Robotics Institute, Beihang University, Beijing, China（北京航空航天大学机器人研究所）；Tongji Hospital, Huazhong University of Science and Technology, Wuhan, China（华中科技大学同济医院）
Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated and deformable convolutions for various image-level segmentation tasks. This gives reason to believe that 3D extensions of such convolutions should also yield performance improvements for video-level segmentation tasks. However, this aspect has not yet been explored thoroughly in existing literature. In this paper, we propose Dynamic Dilated Convolutions (D^2…
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）
MPCM-Net: Multi-scale network integrates partial attention convolution with Mamba for ground-based cloud image segmentation
School of Artificial Intelligence, Hebei University of Technology（河北工业大学人工智能学院）；School of Electrical Engineering, Hebei University of Technology（河北工业大学电气工程学院）；University of Southern Queensland（南方昆士兰大学）；Hebei Province Key Laboratory of Big Data Calculation, Hebei University of Technology（河北省大数据计算重点实验室）；Discipline of Business Systems and Operations, School of Business and Law, Edith Cowan University（商学院与法律学院商业系统与运营学科，埃德温·科温大学）
Costal Cartilage Segmentation with Topology Guided Deformable Mamba: Method and Benchmark
Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College（中国医学科学院北京协和医学院整形外科医院）；School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Nanjing University of Science and Technology（南京理工大学）；The Second Hospital of Hebei Medical University（河北医科大学第二医院）
Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism is far from development. In this paper, we propose the hybrid attention mechanism for single-stage object detection. First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection. In particular, stacked dilated convolution layers with symmetrically fixed rates are constructed to learn spatial attention. The channel attention is proposed with the cross-le…
Multi-level distortion-aware deformable network for omnidirectional image super-resolution
Department of Electrical and Electronic Engineering（电子与电气工程系）；School of Computer Science and Cyber Engineering（计算机科学与网络工程学院）；School of Computer Science（计算机科学学院）
UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images
School of Computer Technology and Applications, Qinghai University（青海大学计算机技术与应用学院）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
University of Zagreb, Faculty of Electrical Engineering and Computing（萨格勒布大学电气工程与计算学院）；Rimac Automobili（锐马克汽车）
Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able …
MambaBEV: An EV-based 3D detection model with Mamba2
School of Instrument Science and Engineering, Southeast University, China（仪器科学与工程学院，东南大学，中国）；Amazon Development Center Germany GmbH, Germany（亚马逊德国开发中心，德国）；T3CAIC Technology, China（T3CAIC技术，中国）；School of Mechanical Engineering, Southeast University, China（机械工程学院，东南大学，中国）
Salient Object Detection in Traffic Scene through the TSOD10K Dataset
College of Information Science and Engineering, Hunan Normal University（湖南师范大学信息科学与工程学院）；College of Artificial Intelligence, Nankai University（南开大学人工智能学院）；National Engineering Research Center of Robot Visual Perception and Control Technology, School of Robotics, Hunan University（湖南大学机器人学院机器人视觉感知与控制技术国家工程研究中心）
Global and Local Mamba Network for Multi-Modality Medical Image Super-Resolution
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Hunan Engineering Research Center of Machine Vision and Intelligent Medicine, Central South University（中南大学机器视觉与智能医学湖南省工程研究中心）；University of Rouen-Normandy（鲁昂-诺曼底大学）；Henri Becquerel Cancer Center（亨利·贝克勒尔癌症中心）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research AI（IBM 研究院人工智能部门）
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features followed by temporal modeling to capture long-term dependencies. While most recent papers have focused on the latter (long-temporal modeling), here, we focus on producing features capable of modeling fine-grained motion more efficiently. We propose a novel locally-consistent deformable convolution, which utilizes the change in receptive fields and enforces a local …
Deformable Feature Alignment and Refinement for Moving Infrared Dim-small Target Detection
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）
MSR:Hybrid Field Modeling for CT-MRI Rigid-Deformable Registration of the Cervical Spine with an Annotated Dataset
School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China.（南方医科大学生物医学工程学院）；Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou, 510515, China.（广东省医学图像处理重点实验室）；Guangdong Province Engineering Laboratory for Medical Imaging（广东省医学影像与诊断技术工程实验室）；Information Center, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China.（南方医科大学南华医院信息中心）；Division of Spine Surgery, Department of Orthopaedics, Nanfang hospital, Southern Medical University, Guangzhou, Guangdong, 510515, China.（南方医科大学南华医院骨科脊柱外科）
Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家级重点实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）；Xi’an Jiaotong University（西安交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention
Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada（电气与计算机工程系，康科迪亚大学，蒙特利尔，加拿大）；Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada（计算机科学与软件工程系，康科迪亚大学，蒙特利尔，加拿大）
Zhejiang University（浙江大学）；University of Washington（华盛顿大学）；Hangzhou Dianzi University（杭州电子科技大学）；Guangdong University of Petrochemical Technology（广东石油化工学院）
Multi-object tracking (MOT) is an essential task in the computer vision field. With the fast development of deep learning technology in recent years, MOT has achieved great improvement. However, some challenges still remain, such as sensitiveness to occlusion, instability under different lighting conditions, non-robustness to deformable objects, etc. To address such common challenges in most of the existing trackers, in this paper, a tracklet booster algorithm is proposed, which can be built upon any other tracker. The motivation is simple and straightforward: split tracklets on potential ID-s…
OCTAMamba: A State-Space Model Approach for Precision OCTA Vasculature Segmentation
College of Artificial Intelligence, Nanjing Agricultural University（南京农业大学人工智能学院）；College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机学院）；Institute of Advanced Technology, Nanjing University of Posts and Telecommunications（南京邮电大学先进技术研究院）；Provincial Key Laboratory for Computer Information Processing Technology, Soochow University（苏州大学计算机信息处理技术省级重点实验室）
