Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images

• URL: http://arxiv.org/abs/2511.09891v1
• Date: Fri, 14 Nov 2025 01:16:56 GMT
• Title: Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images
• Authors: Jinfu Li, Yuqi Huang, Hong Song, Ting Wang, Jianghan Xia, Yucong Lin, Jingfan Fan, Jian Yang,
• Abstract summary: We propose a Scale-Aware Relay Layer (SARL) and a Scale-Adaptive Loss (SAL) for tiny object detection.<n> SARL employs a cross-scale spatial-channel attention to progressively enrich the meaningful features of each layer.<n>SAL reshapes the vanilla IoU-based losses so as to dynamically assign lower weights to larger objects.
• Score: 22.70176024890317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, despite the remarkable advancements in object detection, modern detectors still struggle to detect tiny objects in aerial images. One key reason is that tiny objects carry limited features that are inevitably degraded or lost during long-distance network propagation. Another is that smaller objects receive disproportionately greater regression penalties than larger ones during training. To tackle these issues, we propose a Scale-Aware Relay Layer (SARL) and a Scale-Adaptive Loss (SAL) for tiny object detection, both of which are seamlessly compatible with the top-performing frameworks. Specifically, SARL employs a cross-scale spatial-channel attention to progressively enrich the meaningful features of each layer and strengthen the cross-layer feature sharing. SAL reshapes the vanilla IoU-based losses so as to dynamically assign lower weights to larger objects. This loss is able to focus training on tiny objects while reducing the influence on large objects. Extensive experiments are conducted on three benchmarks (\textit{i.e.,} AI-TOD, DOTA-v2.0 and VisDrone2019), and the results demonstrate that the proposed method boosts the generalization ability by 5.5\% Average Precision (AP) when embedded in YOLOv5 (anchor-based) and YOLOx (anchor-free) baselines. Moreover, it also promotes the robust performance with 29.0\% AP on the real-world noisy dataset (\textit{i.e.,} AI-TOD-v2.0).

Related papers

• HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography [0.0]
  This paper proposes HierLight-YOLO, a hierarchical feature fusion and lightweight model that enhances the real-time detection of small objects.<n>We propose the Hierarchical Extended Path Aggregation Network (HEPAN), a multi-scale feature fusion method through hierarchical cross-level connections.<n>Small object detection head is designed to further enhance spatial resolution and feature fusion to tackle the tiny object (4 pixels) detection.
  arXiv  Detail & Related papers  (2025-09-26T13:59:02Z)
• DASSF: Dynamic-Attention Scale-Sequence Fusion for Aerial Object Detection [6.635903943457569]
  The original YOLO algorithm has low overall detection accuracy due to its weak ability to perceive targets of different scales. This paper proposes a dynamic-attention scale-sequence fusion algorithm (DASSF) for small target detection in aerial images. Experimental results show that when the DASSF method is applied to YOLOv8, compared to YOLOv8n, the model shows an increase of 9.2% and 2.4% in the mean average precision (mAP)
  arXiv  Detail & Related papers  (2024-06-18T05:26:44Z)
• Better Sampling, towards Better End-to-end Small Object Detection [7.7473020808686694]
  Small object detection remains unsatisfactory due to limited characteristics and high density and mutual overlap. We propose methods enhancing sampling within an end-to-end framework. Our model demonstrates a significant enhancement, achieving a 2.9% increase in average precision (AP) over the state-of-the-art (SOTA) on the VisDrone dataset.
  arXiv  Detail & Related papers  (2024-05-17T04:37:44Z)
• Improving the Detection of Small Oriented Objects in Aerial Images [0.0]
  We propose a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss) Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances.
  arXiv  Detail & Related papers  (2024-01-12T11:00:07Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime [2.292003207440126]
  In Few-Shot Object Detection (FSOD), detecting small objects is extremely difficult. We propose Scale-adaptive Intersection over Union (SIoU), a novel box similarity measure. SIoU changes with the objects' size, it is more lenient with small object shifts.
  arXiv  Detail & Related papers  (2023-07-17T07:26:58Z)
• 3D Small Object Detection with Dynamic Spatial Pruning [62.72638845817799]
  We propose an efficient feature pruning strategy for 3D small object detection. We present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects.
  arXiv  Detail & Related papers  (2023-05-05T17:57:04Z)
• SALISA: Saliency-based Input Sampling for Efficient Video Object Detection [58.22508131162269]
  We propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection. We show that SALISA significantly improves the detection of small objects.
  arXiv  Detail & Related papers  (2022-04-05T17:59:51Z)
• A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery [94.78943497436492]
  We present YOLO-S, a simple, fast and efficient network for small target detection. YOLO-S exploits a small feature extractor based on Darknet20, as well as skip connection, via both bypass and concatenation. YOLO-S has an 87% decrease of parameter size and almost one half FLOPs of YOLOv3, making practical the deployment for low-power industrial applications.
  arXiv  Detail & Related papers  (2022-04-05T16:29:49Z)
• EDN: Salient Object Detection via Extremely-Downsampled Network [66.38046176176017]
  We introduce an Extremely-Downsampled Network (EDN), which employs an extreme downsampling technique to effectively learn a global view of the whole image. Experiments demonstrate that EDN achieves sArt performance with real-time speed.
  arXiv  Detail & Related papers  (2020-12-24T04:23:48Z)
• SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing [131.04304632759033]
  Small and cluttered objects are common in real-world which are challenging for detection. In this paper, we first innovatively introduce the idea of denoising to object detection. Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.
  arXiv  Detail & Related papers  (2020-04-28T06:03:54Z)

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.