LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection

• URL: http://arxiv.org/abs/2606.25312v1
• Date: Wed, 24 Jun 2026 02:25:54 GMT
• Title: LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection
• Abstract summary: We introduce LEVIRDet-159, the largest and most comprehensive remote sensing object detection dataset to date.<n>In each key scale dimension, LEVIRDet-159 exceeds the corresponding largest existing remote sensing object detection dataset.<n>We design LEVIRDetNet, a scale-hierarchy-aware detection foundation model for universal remote sensing object detection.
• Score: 29.954536867317575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Remote sensing object detection has advanced rapidly with the development of large-scale benchmarks and modern detection architectures. However, existing datasets and detectors remain fragmented. Most benchmarks focus on limited categories, fixed spatial resolutions, or a single sensor, while detectors still struggle to work across different sensors and categorical systems. In this paper, we introduce LEVIRDet-159, the largest and most comprehensive remote sensing object detection dataset to date, with 159 categories, 2.56 million bounding boxes, and 700k fine-grained annotations under a multi-level taxonomy. In each key scale dimension, LEVIRDet-159 exceeds the corresponding largest existing remote sensing object detection dataset, containing approximately (7x) more images, (6x) more object instances, and (4x) more categories. Based on this dataset, we design LEVIRDetNet, a scale-hierarchy-aware detection foundation model for universal remote sensing object detection. LEVIRDetNet couples online visual Ground Sampling Distance (GSD) prediction, GSD-conditioned query modulation and allocation, and a hierarchy-aware detection head for mixed-granularity remote sensing supervision. Under stringent evaluation settings, LEVIRDetNet demonstrates strong cross-domain generalization. Even without target-domain training or fine-tuning, it achieves state-of-the-art detection performance on 9 external benchmarks, improving the strongest fully supervised competing methods by 5.02 mAP on average under each benchmark's primary metric. We hope this study will facilitate the development of strongly generalizable remote sensing object detection across diverse category systems, spatial resolutions, and sensor platforms. The dataset and trained models will be released at https://qinzheyang.github.io/LEVIRDet/, accompanying the final paper.

Related papers

• OD-VIRAT: A Large-Scale Benchmark for Object Detection in Realistic Surveillance Environments [1.6997584834278812]
  We present two visual object detection benchmarks named OD-VIRAT Large and OD-VIRAT Tiny.<n>The video sequences in both benchmarks cover 10 different scenes of human surveillance recorded from significant height and distance.<n>The proposed benchmarks offer rich annotations of bounding boxes and categories, where OD-VIRAT Large has 8.7 million annotated instances in 599,996 images and OD-VIRAT Tiny has 288,901 annotated instances in 19,860 images.
  arXiv  Detail & Related papers  (2025-07-16T16:41:47Z)
• Generalization-Enhanced Few-Shot Object Detection in Remote Sensing [22.411751110592842]
  Few-shot object detection (FSOD) targets object detection challenges in data-limited conditions.<n>We propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing tasks.<n>Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN), the Multi-Stage Refinement Region Proposal Network (MRRPN), and the Generalized Classification Loss (GCL)
  arXiv  Detail & Related papers  (2025-01-05T08:12:25Z)
• SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection [68.18620488664187]
  We propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++.<n> Specifically, we observe that objects from aerial images usually have arbitrary orientations, small scales, and dense distribution.<n>Extensive experiments conducted on various oriented object under various labeled settings demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-07-01T07:03:51Z)
• LSKNet: A Foundation Lightweight Backbone for Remote Sensing [78.29112381082243]
  This paper proposes a lightweight Large Selective Kernel Network (LSKNet) backbone.<n>LSKNet can adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios.<n>Without bells and whistles, our lightweight LSKNet sets new state-of-the-art scores on standard remote sensing classification, object detection and semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2024-03-18T12:43:38Z)
• SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection [79.23689506129733]
  We establish a new benchmark dataset and an open-source method for large-scale SAR object detection.<n>Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets.<n>To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
  arXiv  Detail & Related papers  (2024-03-11T09:20:40Z)
• Cascade-DETR: Delving into High-Quality Universal Object Detection [99.62131881419143]
  We introduce Cascade-DETR for high-quality universal object detection. We propose the Cascade Attention layer, which explicitly integrates object-centric information into the detection decoder. Lastly, we introduce a universal object detection benchmark, UDB10, that contains 10 datasets from diverse domains.
  arXiv  Detail & Related papers  (2023-07-20T17:11:20Z)
• Large Selective Kernel Network for Remote Sensing Object Detection [96.30162456627784]
  We propose the Large Selective Kernel Network (LSKNet) LSKNet can adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. We rank 2nd place in 2022 the Greater Bay Area International Algorithm Competition.
  arXiv  Detail & Related papers  (2023-03-16T02:00:37Z)
• Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art [7.74389937337756]
  This paper reviews current datasets and object detection methods (deep learning-based) for remote sensing images. We propose a large-scale, publicly available benchmark Remote Sensing Super-resolution Object Detection dataset. We also propose a novel Multi-class Cyclic super-resolution Generative adversarial network with Residual feature aggregation (MCGR) and auxiliary YOLOv5 detector to benchmark image super-resolution-based object detection.
  arXiv  Detail & Related papers  (2021-11-05T04:56:34Z)
• Robust Object Detection via Instance-Level Temporal Cycle Confusion [89.1027433760578]
  We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf) For each object, the task is to find the most different object proposals in the adjacent frame in a video and then cycle back to itself for self-supervision.
  arXiv  Detail & Related papers  (2021-04-16T21:35:08Z)
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery [21.9319970004788]
  We propose a novel benchmark dataset with more than 1 million instances and more than 15,000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery. All objects in the FAIR1M dataset are annotated with respect to 5 categories and 37 sub-categories by oriented bounding boxes.
  arXiv  Detail & Related papers  (2021-03-09T17:20:15Z)

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.