Precise detection of tiny objects in remote sensing imagery remains a significant challenge due to their limited visual information and frequent occurrence within scenes. This challenge is further exacerbated by the practical burden and inherent errors associated with manual annotation: annotating tiny objects is laborious and prone to errors (i.e., label noise). Training detectors for such objects using noisy labels often leads to suboptimal performance, with networks tending to overfit on noisy labels. In this study, we address the intricate issue of tiny object detection under noisy label supervision. We systematically investigate the impact of various types of noise on network training, revealing the vulnerability of object detectors to class shifts and inaccurate bounding boxes for tiny objects. To mitigate these challenges, we propose a DeNoising Tiny Object Detector (DN-TOD), which incorporates a Class-aware Label Correction (CLC) scheme to address class shifts and a Trend-guided Learning Strategy (TLS) to handle bounding box noise. CLC mitigates inaccurate class supervision by identifying and filtering out class-shifted positive samples, while TLS reduces noisy box-induced erroneous supervision through sample reweighting and bounding box regeneration. Additionally, Our method can be seamlessly integrated into both one-stage and two-stage object detection pipelines. Comprehensive experiments conducted on synthetic (i.e., noisy AI-TOD-v2.0 and DOTA-v2.0) and real-world (i.e., AI-TOD) noisy datasets demonstrate the robustness of DN-TOD under various types of label noise. Notably, when applied to the strong baseline RFLA, DN-TOD exhibits a noteworthy performance improvement of 4.9 points under 40% mixed noise. Datasets, codes, and models will be made publicly available.
D$^3$R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, Chinese Academy of Sciences（中国科学院地理空间信息处理与应用系统重点实验室）；Key Laboratory of Target Cognition and Application Technology, Chinese Academy of Sciences（中国科学院目标认知与应用技术重点实验室）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images
School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）；School of Optics and Photonics, Beijing Institute of Technology（光学与 photonics 学院，北京理工大学）
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Box-supervised instance segmentation has recently attracted lots of research efforts while little attention is received in aerial image domain. In contrast to the general object collections, aerial objects have large intra-class variances and inter-class similarity with complex background. Moreover, there are many tiny objects in the high-resolution satellite images. This makes the recent pairwise affinity modeling method inevitably to involve the noisy supervision with the inferior results. To tackle these problems, we propose a novel aerial instance segmentation approach, which drives the ne…
University of Amsterdam（阿姆斯特丹大学）；The University of Tokyo（东京大学）
Detecting tiny objects in a high-resolution video is challenging because the visual information is little and unreliable. Specifically, the challenge includes very low resolution of the objects, MPEG artifacts due to compression and a large searching area with many hard negatives. Tracking is equally difficult because of the unreliable appearance, and the unreliable motion estimation. Luckily, we found that by combining this two challenging tasks together, there will be mutual benefits. Following the idea, in this paper, we present a neural network model called the Recurrent Correlational Netw…
DPNet: Dynamic Pooling Network for Tiny Object Detection
School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机科学学院）；Research Center for Space Computing System, Zhejiang Lab（浙江实验室空间计算系统研究中心）；SWJTU-LEEDS Joint School, Southwest Jiaotong University（西南交通大学SWJTU-LEEDS联合学院）；Guangdong Zhiyun City construction Technology Co., LTD（广东智云城市建设技术有限公司）；Department of Control Science and Engineering, College of Electronic and Information Engineering, Tongji University（同济大学控制科学与工程系）；Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University（河海大学航海智能网络信息科技重点实验室）
Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Di…
Unmanned aerial vehicles (UAVs) with mounted cameras have the advantage of capturing aerial (bird-view) images. The availability of aerial visual data and the recent advances in object detection algorithms led the computer vision community to focus on object detection tasks on aerial images. As a result of this, several aerial datasets have been introduced, including visual data with object annotations. UAVs are used solely as flying-cameras in these datasets, discarding different data types regarding the flight (e.g., time, location, internal sensors). In this work, we propose a multi-purpose…
Inception Institute of Artificial Intelligence, UAE（阿联酋Inception人工智能研究所）；Wuhan University, China（中国武汉大学）；Huazhong University of Science and Technology, China（中国华中科技大学）
Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks. In comparison to instance segmentation in natural scenes, aerial images present unique challenges e.g., a huge number of instances per image, large object-scale variations and abundant tiny objects. Our large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID) comes with 655,451 object ins…
Agricultural Information Institute, Chinese Academy of Agricultural Sciences（中国农业科学院农业信息研究所）；Leibniz Institute for Agricultural Engineering and Bioeconomy（莱布尼茨农业工程与生物经济研究所）
In precision crop protection, (target-orientated) object detection in image processing can help navigate Unmanned Aerial Vehicles (UAV, crop protection drones) to the right place to apply the pesticide. Unnecessary application of non-target areas could be avoided. Deep learning algorithms dominantly use in modern computer vision tasks which require high computing time, memory footprint, and power consumption. Based on the Edge Artificial Intelligence, we investigate the main three paths that lead to dealing with this problem, including hardware accelerators, efficient algorithms, and model com…
Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Freiburg（弗莱堡大学）；Hangzhou City University（杭州城市大学）；XGRIDS（XGRIDS公司）；Fudan University（复旦大学）；Hong Kong Baptist University（香港浸会大学）
Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform. This paper investigates optimizing the detection head based on the sparse convolution, which proves effective in balancing the accuracy and efficiency. Nevertheless, it suffers from inadequate integration of contextual information of tiny objects as well as clumsy control of the mask ratio in the presence of foreground with varying scales. To address the issues above, we propose a novel global context-enhanced adaptive sparse convolutional n…
Computer Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM)（计算机工程系，国王法赫德石油与矿物大学）；SDAIA-KFUPM Joint Research Center on Artificial Intelligence, IRC for Intelligent Secure Systems and Department of Computer Engineering, KFUPM（SDAIA-KFUPM人工智能联合研究中心，智能安全系统研究院及计算机工程系，KFUPM）；Center for Intelligent Secure Systems and the Department of Computer Engineering, King Fahd University of Petroleum & Minerals（智能安全系统中心及计算机工程系，国王法赫德石油与矿物大学）；Research Chair of Pervasive and Mobile Computing, Department of Software Engineering, College of Computer and Information Sciences, King Saud University（普及与移动计算研究主席，软件工程系，计算机与信息科学学院，国王沙特大学）
本文提出TinyEcoWeedNet，通过结构化剪枝、量化感知训练和TensorRT加速，在Jetson Orin Nano上实现184 FPS实时杂草检测，模型缩小68.5%，并在CottonWeedDet12上以85.9% mAP50超越YOLO11n和YOLO12n。
Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detection
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects. Most existing methods employed Feature Pyramid Network (FPN) to enrich shallow layers' features by combing deep layers' contextual features. However, under the limitation of the inconsistency in gradient computation across different layers, the shallow layers in FPN are not fully exploited to detect tiny objects. In this paper, we propose a Scale Selection Pyr…
AIT Austrian Institute of Technology, Center for Digital Safety & Security（奥地利技术学院（AIT）数字安全与保障中心）；TU Wien, Institute of Visual Computing & Human-Centered Technology（维也纳技术大学视觉计算与以人类为中心技术研究所）
Vehicle detection in aerial and satellite images is still challenging due to their tiny appearance in pixels compared to the overall size of remote sensing imagery. Classical methods of object detection very often fail in this scenario due to violation of implicit assumptions made such as rich texture, small to moderate ratios between image size and object size. Satellite video is a very new modality which introduces temporal consistency as inductive bias. Approaches for vehicle detection in satellite video use either background subtraction, frame differencing or subspace methods showing moder…
National University of Defense Technology（国防科技大学）；Sun Yat-sen University（中山大学）
Space-based infrared tiny ship detection aims at separating tiny ships from the images captured by earth orbiting satellites. Due to the extremely large image coverage area (e.g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices. Existing short imaging distance-based infrared datasets and target detection methods cannot be well adopted to the space-based surveillance task. To address these problems, we develop a space-based infrared tiny ship detection dataset (nam…
COMSATS University Islamabad（COMSATS伊斯兰堡大学）；Zhejiang University（浙江大学）
Technological advancements have normalized the usage of unmanned aerial vehicles (UAVs) in every sector, spanning from military to commercial but they also pose serious security concerns due to their enhanced functionalities and easy access to private and highly secured areas. Several instances related to UAVs have raised security concerns, leading to UAV detection research studies. Visual techniques are widely adopted for UAV detection, but they perform poorly at night, in complex backgrounds, and in adverse weather conditions. Therefore, a robust night vision-based drone detection system is …
RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery
University of California, Santa Barbara（加州大学圣芭芭拉分校）；Smithsonian National Zoo and Conservation Biology Institute（史密森尼国家动物园与保护生物学研究所）；Stanford University（斯坦福大学）；The Doris Duke Foundation（多里斯·杜克基金会）
Despite the breakthrough deep learning performances achieved for automatic object detection, small target detection is still a challenging problem, especially when looking at fast and accurate solutions suitable for mobile or edge applications. In this work we present YOLO-S, a simple, fast and efficient network for small target detection. The architecture exploits a small feature extractor based on Darknet20, as well as skip connection, via both bypass and concatenation, and reshape-passthrough layer to alleviate the vanishing gradient problem, promote feature reuse across network and combine…
BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision
School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Instrument Science and Engineering, Southeast University（东南大学仪器科学与工程学院）；Suzhou Institute of Nano-tech and Nano-bionics, Chinese Academy of Sciences（中国科学院苏州纳米技术与纳米仿生研究所）；Department of Computer Science, Stony Brook University（石溪大学计算机科学系）；Biostatistics & Medical Informatics Computer Sciences, University of Wisconsin-Madison（威斯康星大学麦迪逊分校生物统计学与医学信息学计算机科学系）
