LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection

• URL: http://arxiv.org/abs/2605.20667v1
• Date: Wed, 20 May 2026 03:33:13 GMT
• Title: LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection
• Abstract summary: We propose LER-YOLO, a reliability-aware sparse mixture-of-experts framework for RGB-infrared UAV detection.<n>Experiments on the public MBU benchmark under a YOLOv5s-family protocol show that LER-YOLO achieves 89.7 +/-0.2% AP50 over three independent seeds, with a best result of 89.9%.
• Score: 6.816296803605649
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and spatial misalignment between heterogeneous sensors. Existing bimodal detectors often align or fuse features without assessing the reliability of local cross-sensor correspondence, allowing mismatch artifacts to propagate into the detection head. To address this issue, we propose LER-YOLO, a reliability-aware sparse mixture-of-experts framework for misaligned RGB-infrared UAV detection. LER-YOLO first introduces an Uncertainty-Aware Target Alignment module that resamples visible features toward the infrared reference and estimates a spatial reliability map. This reliability prior is then used by a Reliability-Guided Sparse MoE Fusion module to adaptively select k experts from RGB-dominant, infrared-dominant, and interactive fusion experts, enabling trustworthy cross-modal interaction while suppressing unreliable fusion. Experiments on the public MBU benchmark under a YOLOv5s-family protocol show that LER-YOLO achieves 89.7+/-0.2% AP50 over three independent seeds, with a best result of 89.9%. Extensive ablations, parameter-matched comparisons, synthetic-shift evaluations, and complexity analysis demonstrate that the gains mainly come from reliability-guided expert routing rather than increased model capacity.

Related papers

• Uncertainty-Aware Multimodal Anti-UAV Detection via Evidential Fusion and Conflict-Discounted Belief Aggregation [0.0]
  multimodal anti-UAV systems fuse RGB and thermal streams deterministically, without modeling predictive uncertainty.<n>This paper extends EDTC to multimodal RGB-Thermal perception via Discounted Belief Fusion (DBF)<n>On the Anti-UAV benchmark, multimodal fusion consistently outperforms either single stream.
  arXiv  Detail & Related papers  (2026-08-29T12:48:22Z)
• EGM-Det: Entropy-Guided Multimodal Adaptive Fusion for UAV RGB-IR Object Detection [11.826446098340048]
  We propose EGM-Det, an entropy-guided adaptive fusion framework for RGB-IR object detection.<n>EGM-Det employs a dual-stream architecture to preserve modality-specific representations.<n>It selectively aggregates reliable RGB and infrared cues instead of uniformly combining heterogeneous features.
  arXiv  Detail & Related papers  (2026-08-12T05:51:48Z)
• Reusing Fusion-Time Spectral Reliability for Adaptive Fusion and Expert Routing in RGB-Infrared Object Detection [0.0]
  We propose to extract a parameter-free, 7-dimensional spectral reliability descriptor.<n>Describes band energy, amplitude ratio, phase consistency, and cross-modal correlation.<n>We show that preserving fusion-time reliability as an explicit signal benefits both adaptive fusion and post-fusion conditional computation.
  arXiv  Detail & Related papers  (2026-05-31T11:28:41Z)
• Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling [49.887347082863194]
  We show that relative thermal radiation relations between different classes can be regarded as a reliable knowledge source under the complex scenarios of adversarial examples and common corruptions.<n>We propose Knowledge-Guided Adversarial Training (KGAT) for infrared object detection, in which infrared physical knowledge is embedded into the adversarial training process.
  arXiv  Detail & Related papers  (2026-03-26T08:43:43Z)
• Alignment-Aware and Reliability-Gated Multimodal Fusion for Unmanned Aerial Vehicle Detection Across Heterogeneous Thermal-Visual Sensors [6.686898063543218]
  This study introduces two fusion strategies, Registration-aware Guided Image Fusion (RGIF) and Reliability-Gated Modality-Attention Fusion (RGMAF)<n>RGIF employs Enhanced Correlation Coefficient (ECC)-based affine registration combined with guided filtering to maintain thermal saliency while enhancing structural detail.<n>RGMAF integrates affine and optical-flow registration with a reliability-weighted attention mechanism that adaptively balances thermal contrast and visual sharpness.
  arXiv  Detail & Related papers  (2026-03-09T10:39:26Z)
• Small Target Detection Based on Mask-Enhanced Attention Fusion of Visible and Infrared Remote Sensing Images [8.72869311285096]
  This work presents ESM-YOLO+ as a lightweight visible infrared fusion network.<n>To enhance detection, ESM-YOLO+ includes two key innovations.<n>ESM-YOLO+ integrates strong performance with practicality for real-time deployment.
  arXiv  Detail & Related papers  (2026-03-06T22:53:27Z)
• MambaRefine-YOLO: A Dual-Modality Small Object Detector for UAV Imagery [1.005854289245731]
  Small object detection in Unmanned Aerial Vehicle (UAV) imagery is a persistent challenge, hindered by low resolution and background clutter.<n>We introduce Mamba-YOLO, a fusion module that balances RGB and IR modalities through illumination-aware and difference-aware gating mechanisms.<n>Our work presents a superior balance between accuracy and speed, making it highly suitable for real-world UAV applications.
  arXiv  Detail & Related papers  (2025-11-24T13:59:01Z)
• Multispectral Detection Transformer with Infrared-Centric Feature Fusion [8.762314897895175]
  Infrared-Centric Fusion (IC-Fusion) is a lightweight and modality-aware sensor fusion method.<n>IC-Fusion prioritizes infrared features while effectively integrating complementary RGB semantic context.<n> Experiments on the FLIR and LLVIP benchmarks demonstrate the superior effectiveness and efficiency of our IR-centric fusion strategy.
  arXiv  Detail & Related papers  (2025-05-21T05:44:14Z)
• Multi-Domain Biometric Recognition using Body Embeddings [51.36007967653781]
  We show that body embeddings perform better than face embeddings in medium-wave infrared (MWIR) and long-wave infrared (LWIR) domains.<n>We leverage a vision transformer architecture to establish benchmark results on the IJB-MDF dataset.<n>We also show that finetuning a body model, pretrained exclusively on VIS data, with a simple combination of cross-entropy and triplet losses achieves state-of-the-art mAP scores.
  arXiv  Detail & Related papers  (2025-03-13T22:38:18Z)
• Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection [67.02804741856512]
  We propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection.<n>Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions.
  arXiv  Detail & Related papers  (2025-01-25T06:21:06Z)
• Infra-YOLO: Efficient Neural Network Structure with Model Compression for Real-Time Infrared Small Object Detection [4.586010474241955]
  A new dataset named InfraTiny was constructed, and more than 85% bounding box is less than 32x32 pixels (3218 images and a total of 20,893 bounding boxes) A multi-scale attention mechanism module (MSAM) and a Feature Fusion Augmentation Pyramid Module (FFAFPM) were proposed and deployed onto embedded devices. By integrating the proposed methods into the YOLO model, which is named Infra-YOLO, infrared small object detection performance has been improved.
  arXiv  Detail & Related papers  (2024-08-14T10:49:14Z)
• SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection [53.19618419772467]
  Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. With the development of Transformer, the scale of SIRST models is constantly increasing. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
  arXiv  Detail & Related papers  (2024-03-08T16:14:54Z)
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection [65.30079184700755]
  This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network.
  arXiv  Detail & Related papers  (2022-03-30T11:44:56Z)
• Multimodal Object Detection via Bayesian Fusion [59.31437166291557]
  We study multimodal object detection with RGB and thermal cameras, since the latter can provide much stronger object signatures under poor illumination. Our key contribution is a non-learned late-fusion method that fuses together bounding box detections from different modalities. We apply our approach to benchmarks containing both aligned (KAIST) and unaligned (FLIR) multimodal sensor data.
  arXiv  Detail & Related papers  (2021-04-07T04:03:20Z)

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.