The "You only look once v4"(YOLOv4) is one type of object detection methods in deep learning. YOLOv4-tiny is proposed based on YOLOv4 to simple the network structure and reduce parameters, which makes it be suitable for developing on the mobile and embedded devices. To improve the real-time of object detection, a fast object detection method is proposed based on YOLOv4-tiny. It firstly uses two ResBlock-D modules in ResNet-D network instead of two CSPBlock modules in Yolov4-tiny, which reduces the computation complexity. Secondly, it designs an auxiliary residual network block to extract more feature information of object to reduce detection error. In the design of auxiliary network, two consecutive 3x3 convolutions are used to obtain 5x5 receptive fields to extract global features, and channel attention and spatial attention are also used to extract more effective information. In the end, it merges the auxiliary network and backbone network to construct the whole network structure of improved YOLOv4-tiny. Simulation results show that the proposed method has faster object detection than YOLOv4-tiny and YOLOv3-tiny, and almost the same mean value of average precision as the YOLOv4-tiny. It is more suitable for real-time object detection.
Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful techniques for tackling the challenge of object detection, one of the biggest challenges with enabling such object detection networks for widespread deployment on embedded devices is high computational and memory requirements. Recently, there has been an increasing focus in exploring small deep neural network architectures for object detection that are more suitable for embedded d…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of North Electronic Equipment（北方电子设备研究所）
FPN-based detectors have made significant progress in general object detection, e.g., MS COCO and PASCAL VOC. However, these detectors fail in certain application scenarios, e.g., tiny object detection. In this paper, we argue that the top-down connections between adjacent layers in FPN bring two-side influences for tiny object detection, not only positive. We propose a novel concept, fusion factor, to control information that deep layers deliver to shallow layers, for adapting FPN to tiny object detection. After series of experiments and analysis, we explore how to estimate an effective value…
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）
Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object detection methods use standard deep neural networks as their backbone architecture. We argue that such backbones are inappropriate for detecting tiny objects as they are designed for the classification of larger objects, and do not have the spatial resolution to identify small targets. Specifically, such backbones use max-pooling or a large stride at early stages in the architecture. This produces lower resolution featu…
Detecting tiny objects is one of the main obstacles hindering the development of object detection. The performance of generic object detectors tends to drastically deteriorate on tiny object detection tasks. In this paper, we point out that either box prior in the anchor-based detector or point prior in the anchor-free detector is sub-optimal for tiny objects. Our key observation is that the current anchor-based or anchor-free label assignment paradigms will incur many outlier tiny-sized ground truth samples, leading to detectors imposing less focus on the tiny objects. To this end, we propose…
Object detection has made great progress in the past few years along with the development of deep learning. However, most current object detection methods are resource hungry, which hinders their wide deployment to many resource restricted usages such as usages on always-on devices, battery-powered low-end devices, etc. This paper considers the resource and accuracy trade-off for resource-restricted usages during designing the whole object detection framework. Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages. Tiny-D…
Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance information. Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors. To alleviate this, we propose a new evaluation metric using Wasserstein distance f…
Annotating tens or hundreds of tiny objects in a given image is laborious yet crucial for a multitude of Computer Vision tasks. Such imagery typically contains objects from various categories, yet the multi-class interactive annotation setting for the detection task has thus far been unexplored. To address these needs, we propose a novel interactive annotation method for multiple instances of tiny objects from multiple classes, based on a few point-based user inputs. Our approach, C3Det, relates the full image context with annotator inputs in a local and global manner via late-fusion and featu…
COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
Beijing Institute of Technology（北京理工大学）；National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）；National Key Laboratory of Space Target Awareness, Space Engineering University（航天工程大学空间目标感知全国重点实验室）；Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China（教育部光电成像技术与系统重点实验室）；Chongqing Innovation Center, Beijing Institute of Technology（北京理工大学重庆创新中心）；China North Vehicle Research Institute（中国北方车辆研究所）
University of Chinese Academy of Sciences（中国科学院大学）
Visual object detection has achieved unprecedented ad-vance with the rise of deep convolutional neural networks.However, detecting tiny objects (for example tiny per-sons less than 20 pixels) in large-scale images remainsnot well investigated. The extremely small objects raisea grand challenge about feature representation while themassive and complex backgrounds aggregate the risk offalse alarms. In this paper, we introduce a new benchmark,referred to as TinyPerson, opening up a promising directionfor tiny object detection in a long distance and with mas-sive backgrounds. We experimentally fin…
UCAS（中国科学院大学）；NUS（新加坡国立大学）；Pengcheng Lab（鹏城实验室）；Baidu Inc（百度公司）；ICT（中国科学院计算技术研究所）；CAS（中国科学院）；Beihang University（北京航空航天大学）；Southeast University（东南大学）；Sichuan University（四川大学）；U of Oregon（俄勒冈大学）
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection. The TinyPerson dataset was used for the TOD Challenge and is publicly released. It has 1610 images and 72651 box-levelannotations. Around 36 participating teams from the globe competed inthe 1st TOD Challenge. In this paper, we provide a brief summary of the1st TOD Challenge including brief introductions to the top three methods.The submission leaderboard will be reopened for r…
Bridging the Scale Gap: Balanced Tiny and General Object Detection in Remote Sensing Imagery
Key Laboratory of Intelligent Computing & Signal Processing (Anhui University), Ministry of Education（智能计算与信号处理重点实验室（安徽大学））；Anhui Provincial Key Laboratory of Multimodal Cognitive Computation（安徽省多模态认知计算重点实验室）；School of Artificial Intelligence, Anhui University（人工智能学院）；th Research Institute, China Electronics Technology Group Corporation（中国电子科技集团第三十八研究所）；School of Computer Science and Technology, Anhui University（计算机科学与技术学院）
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）
Systems Laboratory, Universit\' e Laval Quebec City (QC), Canada
Current object segmentation algorithms are based on the hypothesis that one has access to a very large amount of data. In this paper, we aim to segment objects using only tiny datasets. To this extent, we propose a new automatic part-based object segmentation algorithm for non-deformable and semi-deformable objects in natural backgrounds. We have developed a novel shape descriptor which models the local boundaries of an object's part. This shape descriptor is used in a bag-of-words approach for object detection. Once the detection process is performed, we use the background and foreground like…
Northeastern University（东北大学）；China Medical University（中国医科大学）；Shengjing Hospital（盛京医院）；Jinghua Hospital（京华医院）；Stevens Institute of Technology（史蒂文斯理工学院）；University of Luebeck（吕贝克大学）
The detection of tiny objects in microscopic videos is a problematic point, especially in large-scale experiments. For tiny objects (such as sperms) in microscopic videos, current detection methods face challenges in fuzzy, irregular, and precise positioning of objects. In contrast, we present a convolutional neural network for tiny object detection (TOD-CNN) with an underlying data set of high-quality sperm microscopic videos (111 videos, $>$ 278,000 annotated objects), and a graphical user interface (GUI) is designed to employ and test the proposed model effectively. TOD-CNN is highly accura…
Recently, the convolutional neural network has brought impressive improvements for object detection. However, detecting tiny objects in large-scale remote sensing images still remains challenging. First, the extreme large input size makes the existing object detection solutions too slow for practical use. Second, the massive and complex backgrounds cause serious false alarms. Moreover, the ultratiny objects increase the difficulty of accurate detection. To tackle these problems, we propose a unified and self-reinforced network called remote sensing region-based convolutional neural network ($\…
This work aims to explore and identify tiny and seemingly unrelated perturbations of images in object detection that will lead to performance degradation. While tininess can naturally be defined using $L_p$ norms, we characterize the degree of "unrelatedness" of an object by the pixel distance between the occurred perturbation and the object. Triggering errors in prediction while satisfying two objectives can be formulated as a multi-objective optimization problem where we utilize genetic algorithms to guide the search. The result successfully demonstrates that (invisible) perturbations on the…
Wave Processes and Control Systems Lab, MIPT（莫斯科物理技术学院波动过程与控制系统实验室）
We propose a method of improving detection precision (mAP) with the help of the prior knowledge about the scene geometry: we assume the scene to be a plane with objects placed on it. We focus our attention on autonomous robots, so given the robot's dimensions and the inclination angles of the camera, it is possible to predict the spatial scale for each pixel of the input frame. With slightly modified YOLOv3-tiny we demonstrate that the detection supplemented by the scale channel, further referred as S, outperforms standard RGB-based detection with small computational overhead.
Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation, dropout) have shown much success on large neural networks by adding noise to overcome over-fitting. However, we found these techniques hurt the performance of tiny neural networks. We argue that training tiny models are different from large models: rather than augmenting the data, we should augment the model, since tiny models tend to suffer from under-fitting rather than over-fitting due to limited capacity. To al…
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）
Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；SenseTime（商汤科技）；The University of Sydney（悉尼大学）
In this paper, we propose a simple and general framework for training very tiny CNNs for object detection. Due to limited representation ability, it is challenging to train very tiny networks for complicated tasks like detection. To the best of our knowledge, our method, called Quantization Mimic, is the first one focusing on very tiny networks. We utilize two types of acceleration methods: mimic and quantization. Mimic improves the performance of a student network by transfering knowledge from a teacher network. Quantization converts a full-precision network to a quantized one without large d…
A DeNoising FPN With Transformer R-CNN for Tiny Object Detection
Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University（电子工程系，阳明交通大学）；Institute of Electronics, National Yang Ming Chiao Tung University（电子研究所，阳明交通大学）；Department of Computer Science and Information Engineering, National Taiwan University (NTU)（计算机科学与信息工程系，国立台湾大学）
University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）；Las Cumbres Observatory（拉斯坎布雷斯天文台）
We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detecting cosmic rays (CRs) in astronomical observations is a cumbersome workflow that requires multiple tools, so we developed an interactive toolkit that unifies model inference, HDR image visualization, segmentation mask inspection and editing into a single graphical user interface. The feature set, initially designed for astronomical data, makes this work a useful research-supporti…
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…
SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection
Shenzhen University, Shenzhen, China The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou, China The Hong Kong University of Science；Technology (Guangzhou), Guangzhou, China Jilin University, Changchun, China Guangdong ACXEL Micro \& Nano Tech Co., Ltd., Guangzhou, China
University of Waterloo（滑铁卢大学）；DarwinAI Corp.（DarwinAI公司）
Object detection remains an active area of research in the field of computer vision, and considerable advances and successes has been achieved in this area through the design of deep convolutional neural networks for tackling object detection. Despite these successes, one of the biggest challenges to widespread deployment of such object detection networks on edge and mobile scenarios is the high computational and memory requirements. As such, there has been growing research interest in the design of efficient deep neural network architectures catered for edge and mobile usage. In this study, w…
Semantic-Guided Natural Language and Visual Fusion for Cross-Modal Interaction Based on Tiny Object Detection
Department of Electrical Engineering, National Formosa University, Taiwan（台湾国立Formosa大学电子工程系）；Department of Electrical Engineering, National Taipei University, Taiwan（台湾国立台北大学电子工程系）；College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, Taiwan（台湾国立阳明交通大学人工智能与再生能源学院）
ZHAW Datalab（苏黎世应用科技大学数据实验室）；USI（瑞士意大利语区大学）；University of Venice（威尼斯大学）；IDSIA（人工智能研究所）
We present the DeepScores dataset with the goal of advancing the state-of-the-art in small objects recognition, and by placing the question of object recognition in the context of scene understanding. DeepScores contains high quality images of musical scores, partitioned into 300,000 sheets of written music that contain symbols of different shapes and sizes. With close to a hundred millions of small objects, this makes our dataset not only unique, but also the largest public dataset. DeepScores comes with ground truth for object classification, detection and semantic segmentation. DeepScores t…
University of Waterloo（滑铁卢大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）；DarwinAI Corp.（DarwinAI公司）
In this study, we introduce \textbf{AttendSeg}, a low-precision, highly compact deep neural network tailored for on-device semantic segmentation. AttendSeg possesses a self-attention network architecture comprising of light-weight attention condensers for improved spatial-channel selective attention at a very low complexity. The unique macro-architecture and micro-architecture design properties of AttendSeg strike a strong balance between representational power and efficiency, achieved via a machine-driven design exploration strategy tailored specifically for the task at hand. Experimental res…
UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects
Easy Lab, College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China（易实验室，数学与信息学院，华南农业大学，广州，中国）；School of Computer Science and Engineering, Southeast University, Nanjing, China（计算机科学与工程学院，东南大学，南京，中国）；School of Mathematics, Foshan University, Foshan, China（数学学院，佛山大学，佛山，中国）
