UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection

• URL: http://arxiv.org/abs/2507.00849v1
• Date: Tue, 01 Jul 2025 15:21:27 GMT
• Title: UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection
• Authors: Wei Li, Jiaman Tang, Yang Li, Beihao Xia, Ligang Tan, Hongmao Qin,
• Abstract summary: UAVD-Mamba is a multimodal UAV object detection framework based on Mamba architectures.<n>To improve geometric adaptability, we propose the Deformable Token Mamba Block (DTMB)<n>To optimize the multimodal feature complementarity, we design two separate DTMBs for the RGB and infrared (IR) modalities.
• Score: 5.89878250955707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unmanned Aerial Vehicle (UAV) object detection has been widely used in traffic management, agriculture, emergency rescue, etc. However, it faces significant challenges, including occlusions, small object sizes, and irregular shapes. These challenges highlight the necessity for a robust and efficient multimodal UAV object detection method. Mamba has demonstrated considerable potential in multimodal image fusion. Leveraging this, we propose UAVD-Mamba, a multimodal UAV object detection framework based on Mamba architectures. To improve geometric adaptability, we propose the Deformable Token Mamba Block (DTMB) to generate deformable tokens by incorporating adaptive patches from deformable convolutions alongside normal patches from normal convolutions, which serve as the inputs to the Mamba Block. To optimize the multimodal feature complementarity, we design two separate DTMBs for the RGB and infrared (IR) modalities, with the outputs from both DTMBs integrated into the Mamba Block for feature extraction and into the Fusion Mamba Block for feature fusion. Additionally, to improve multiscale object detection, especially for small objects, we stack four DTMBs at different scales to produce multiscale feature representations, which are then sent to the Detection Neck for Mamba (DNM). The DNM module, inspired by the YOLO series, includes modifications to the SPPF and C3K2 of YOLOv11 to better handle the multiscale features. In particular, we employ cross-enhanced spatial attention before the DTMB and cross-channel attention after the Fusion Mamba Block to extract more discriminative features. Experimental results on the DroneVehicle dataset show that our method outperforms the baseline OAFA method by 3.6% in the mAP metric. Codes will be released at https://github.com/GreatPlum-hnu/UAVD-Mamba.git.

Related papers

• HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion [9.235004977824026]
  Transparent and reflective objects pose significant challenges for depth sensors.<n>We propose HTMNet, a novel hybrid model integrating Transformer, CNN, and Mamba architectures.<n>We introduce a novel multimodal fusion module grounded in self-attention mechanisms and state space models.
  arXiv  Detail & Related papers  (2025-05-27T08:51:38Z)
• MDDFNet: Mamba-based Dynamic Dual Fusion Network for Traffic Sign Detection [0.081585306387285]
  We propose a novel object detection network, Mamba-based Dynamic Dual Fusion Network (MDDFNet) for traffic sign detection.<n>The network integrates a dynamic dual fusion module and a Mamba-based backbone to simultaneously tackle the aforementioned issues.<n>Extensive experiments conducted on the TT100K (Tsinghua-Tencent 100K) datasets demonstrate that MDDFNet outperforms other state-of-the-art detectors.
  arXiv  Detail & Related papers  (2025-05-02T14:53:25Z)
• DefMamba: Deformable Visual State Space Model [65.50381013020248]
  We propose a novel visual foundation model called DefMamba.<n>By combining a deformable scanning(DS) strategy, this model significantly improves its ability to learn image structures and detects changes in object details.<n>Numerous experiments have shown that DefMamba achieves state-of-the-art performance in various visual tasks.
  arXiv  Detail & Related papers  (2025-04-08T08:22:54Z)
• TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba [88.31117598044725]
  We explore cross-architecture training to transfer the ready knowledge in existing Transformer models to alternative architecture Mamba, termed TransMamba.<n>Our approach employs a two-stage strategy to expedite training new Mamba models, ensuring effectiveness in across uni-modal and cross-modal tasks.<n>For cross-modal learning, we propose a cross-Mamba module that integrates language awareness into Mamba's visual features, enhancing the cross-modal interaction capabilities of Mamba architecture.
  arXiv  Detail & Related papers  (2025-02-21T01:22:01Z)
• MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt [60.10555128510744]
  Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary image information from different modalities.<n>Recently, large-scale pre-trained models like CLIP have demonstrated impressive performance in traditional single-modal object ReID tasks.<n>We introduce a novel framework called MambaPro for multi-modal object ReID.
  arXiv  Detail & Related papers  (2024-12-14T06:33:53Z)
• DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing [8.530409994516619]
  Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. We propose Disparity-guided Multispectral Mamba (DMM), a framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task.
  arXiv  Detail & Related papers  (2024-07-11T02:09:59Z)
• Fusion-Mamba for Cross-modality Object Detection [63.56296480951342]
  Cross-modality fusing information from different modalities effectively improves object detection performance. We design a Fusion-Mamba block (FMB) to map cross-modal features into a hidden state space for interaction. Our proposed approach outperforms the state-of-the-art methods on $m$AP with 5.9% on $M3FD$ and 4.9% on FLIR-Aligned datasets.
  arXiv  Detail & Related papers  (2024-04-14T05:28:46Z)
• MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion [4.2474907126377115]
  Multi-modality image fusion (MMIF) aims to integrate complementary information from different modalities into a single fused image. We propose a Mamba-based Dual-phase Fusion model (MambaDFuse) to extract modality-specific and modality-fused features. Our approach achieves promising fusion results in infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2024-04-12T11:33:26Z)
• Bi-directional Adapter for Multi-modal Tracking [67.01179868400229]
  We propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter. We develop a simple but effective light feature adapter to transfer modality-specific information from one modality to another. Our model achieves superior tracking performance in comparison with both the full fine-tuning methods and the prompt learning-based methods.
  arXiv  Detail & Related papers  (2023-12-17T05:27:31Z)
• Multimodal Industrial Anomaly Detection via Hybrid Fusion [59.16333340582885]
  We propose a novel multimodal anomaly detection method with hybrid fusion scheme. Our model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTecD-3 AD dataset.
  arXiv  Detail & Related papers  (2023-03-01T15:48:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.