Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics. In contrast, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. In this paper, we propose an effective approximate SkewIoU loss based on Gaussian modeling and Gaussian product, which mainly consists of two items. The first term is a scale-insensitive center point loss, which is used to quickly narrow the distance between the center points of the two bounding boxes. In the distance-independent second term, the product of the Gaussian distributions is adopted to inherently mimic the mechanism of SkewIoU by its definition, and show its alignment with the SkewIoU loss at trend-level within a certain distance (i.e. within 9 pixels). This is in contrast to recent Gaussian modeling based rotation detectors e.g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors. The resulting new loss called KFIoU loss is easier to implement and works better compared with exact SkewIoU loss, thanks to its full differentiability and ability to handle the non-overlapping cases. We further extend our technique to the 3-D case which also suffers from the same issues as 2-D. Extensive results on various public datasets (2-D/3-D, aerial/text/face images) with different base detectors show the effectiveness of our approach.
Rotated object detection in aerial images is a meaningful yet challenging task as objects are densely arranged and have arbitrary orientations. The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions. As ln-norm losses are mainly based on non-scale-invariant Minkowski distance, using ln-norm losses will lead to inconsistency with the detection metric rotational Intersection-over-Union (IoU) and training instability. To address the problems, we use Mahalanobis distance to calculate l…
Shanghai Jiao Tong University（上海交通大学）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Institute of Technology（北京理工大学）；Huawei Inc.（华为公司）
Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection due to the limitation of current regression loss design, especially for objects with large aspect ratios. Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation be…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）；Inner Mongolia Key Laboratory of Molecular Biology on Featured Plants（内蒙古特色植物分子生物学重点实验室）
We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration. We introduce a novel modulated rotation loss to alleviate the problem and propose a rotation sensitivity detection network (RSDet) which is consists of an eight-param single-stage rotated object detector and the modulated rotation loss. Our proposed RSDet has several advantages: 1) it reformulates the rotated object detection problem as predicting the corners of objects while most previous methods employ a f…
Shanghai Jiao Tong University（上海交通大学）；Beijing Institute of Technology（北京理工大学）；Huawei Inc.（华为公司）
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even t…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shanghai Jiao Tong University（上海交通大学）
Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function. In this paper, we argue that the aforementioned integration can cause training instability and performance degeneration, due to the loss discontinuity resulted from the inherent periodicity of angles and the associated sudden exchange of width and height. This problem is further pronounced given the regression inconsistency among five parameters with different measurement units. We refer to the…
Small and cluttered objects are common in real-world which are challenging for detection. The difficulty is further pronounced when the objects are rotated, as traditional detectors often routinely locate the objects in horizontal bounding box such that the region of interest is contaminated with background or nearby interleaved objects. 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. To handle the rotation variation, we also add a novel Io…
Rotated object detection in aerial images has received increasing attention for a wide range of applications. However, it is also a challenging task due to the huge variations of scale, rotation, aspect ratio, and densely arranged targets. Most existing methods heavily rely on a large number of pre-defined anchors with different scales, angles, and aspect ratios, and are optimized with a distance loss. Therefore, these methods are sensitive to anchor hyper-parameters and easily suffer from performance degradation caused by boundary discontinuity. To handle this problem, in this paper, we propo…
Rotated object detection is a challenging issue of computer vision field. Loss of spatial information and confusion of parametric order have been the bottleneck for rotated detection accuracy. In this paper, we propose an orientation-sensitive keypoint based rotated detector OSKDet. We adopt a set of keypoints to characterize the target and predict the keypoint heatmap on ROI to form a rotated target. By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for target representation, which imp…
Huazhong University of Science and Technology（华中科技大学）
General detectors follow the pipeline that feature maps extracted from ConvNets are shared between classification and regression tasks. However, there exists obvious conflicting requirements in multi-orientation object detection that classification is insensitive to orientations, while regression is quite sensitive. To address this issue, we provide an Encoder-Decoder architecture, called Rotated Feature Network (RFN), which produces rotation-sensitive feature maps (RS) for regression and rotation-invariant feature maps (RI) for classification. Specifically, the Encoder unit assigns weights fo…
Baidu Research（百度研究院）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术与应用国家工程实验室）；Beijing Institute of Technology（北京理工大学）；Northwestern Polytechnical University（西北工业大学）
In 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage. However, during the training stage, the common distance loss (\eg, $L_1$ or $L_2$) is often adopted as the loss function to minimize the discrepancy between the predicted and ground truth Bounding Box (Bbox). To eliminate the performance gap between training and testing, the IoU loss has been introduced for 2D object detection in \cite{yu2016unitbox} and \cite{rezatofighi2019generalized}. Unfortunately, all these…
Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
Object detection has been a building block in computer vision. Though considerable progress has been made, there still exist challenges for objects with small size, arbitrary direction, and dense distribution. Apart from natural images, such issues are especially pronounced for aerial images of great importance. This paper presents a novel multi-category rotation detector for small, cluttered and rotated objects, namely SCRDet. Specifically, a sampling fusion network is devised which fuses multi-layer feature with effective anchor sampling, to improve the sensitivity to small objects. Meanwhil…
Linear Gaussian Bounding Box Representation and Ring-Shaped Rotated Convolution for Oriented Object Detection
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Object detection using an oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect ratios. Therefore, a novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression. The PIoU loss is …
JetBrains Research（JetBrains研究院）；National Research University Higher School of Economics（国立研究型高等经济学院）
The task object tracking is vital in numerous applications such as autonomous driving, intelligent surveillance, robotics, etc. This task entails the assigning of a bounding box to an object in a video stream, given only the bounding box for that object on the first frame. In 2015, a new type of video object tracking (VOT) dataset was created that introduced rotated bounding boxes as an extension of axis-aligned ones. In this work, we introduce a novel end-to-end deep learning method based on the Transformer Multi-Head Attention architecture. We also present a new type of loss function, which …
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Anhui University（安徽大学）；Cowa Robot, Co Ltd（科沃机器人有限公司）
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection, especially for high-precision detection with high IoU (e.g. 0.75). Instead, we propose to model the rotated objects as Gaussian distributions. A direct advantage is that our new regression loss regarding the distance between two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well…
Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on indoor environments with camera rotation. Indoor, rotated scenes are common for less constrained applications and pose problems for two reasons: abundance of low texture regions and increased complexity of depth cues for images under rotation. In an effort to extend self-supervised learning to more generalised environments we propose two additions. First, w…
PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection
School of Computer Science（计算机科学学院）；Wuhan University（武汉大学）；School of Remote Sensing and Information Engineering（遥感与信息工程学院）；Department of Automation（自动化系）；Shanghai Jiao Tong University（上海交通大学）；School of Automation（自动化学院）；Southeast University（东南大学）；SEIE（电子信息学院）；Harbin Institute of Technology（哈尔滨工业大学）；S-Lab, CCDS（S实验室，CCDS）；Nanyang Technological University（南洋理工大学）；CSE & SAI（计算机科学与工程系及人工智能院）；The Chinese University of Hong Kong（香港中文大学）；Ant Group（蚂蚁集团）；VCIP, CS（VCIP，计算机科学）
Oriented object detection is a challenging task in aerial images since the objects in aerial images are displayed in arbitrary directions and are frequently densely packed. The mainstream detectors describe rotating objects using a five-parament or eight-parament representations, which suffer from representation ambiguity for orientated object definition. In this paper, we propose a novel representation method based on area ratio of parallelogram, called ARP. Specifically, ARP regresses the minimum bounding rectangle of the oriented object and three area ratios. Three area ratios include the a…
PointOBB: Learning Oriented Object Detection via Single Point Supervision
Wuhan University（武汉大学）；Shanghai AI Laboratory（上海人工智能实验室）；Southeast University（东南大学）；Harbin Institute of Technology（哈尔滨工业大学）；Shanghai Jiao Tong University（上海交通大学）
ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
School of Electronics and Information Engineering, Harbin Institute of Technology（哈尔滨工业大学电子与信息工程学院）；OpenGVLab, Shanghai AI Laboratory（上海人工智能实验室OpenGVLab）
Rethinking Boundary Discontinuity Problem for Oriented Object Detection
Hangzhou Dianzi University（杭州电子科技大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Lishui Institute of Hangzhou Dianzi University（杭州电子科技大学丽水研究院）
RADE-Net: Robust Attention Network for Radar-Only Object Detection in Adverse Weather
Infineon Technologies AG（英飞凌科技有限公司）；Institute of Visual Computing（视觉计算研究所）；Graz University of Technology（格拉茨工业大学）；Virtual Vehicle Research GmbH（虚拟车辆研究有限公司）
University of the Chinese Academy of Sciences（中国科学院大学）；University at Albany, SUNY（纽约州立大学奥尔巴尼分校）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；Tencent Youtu Lab（腾讯优图实验室）
Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i.e., feature extraction, region proposal, bounding box regression, and additional layers for rotated region detection. In this paper, we propose a new Scale Invariant Fully Convolutional Network (SIFCN) trained in an end-to-end fashion to detect hands efficiently. Specifically, we merge the feature maps from high to low layers in an iterative way, which handles different scales of hands better with less time overhead comparing to concatenating them simply. Moreover, we develop the Comple…
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Faceall Technology Co.,Ltd（北京飞搜科技有限公司）
We aim to study the multi-scale receptive fields of a single convolutional neural network to detect faces of varied scales. This paper presents our Multi-Scale Receptive Field Face Detector (MSFD), which has superior performance on detecting faces at different scales and enjoys real-time inference speed. MSFD agglomerates context and texture by hierarchical structure. More additional information and rich receptive field bring significant improvement but generate marginal time consumption. We simultaneously propose an anchor assignment strategy which can cover faces with a wide range of scales …
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification…
Deep convolutional neural network with increased number of parameters has achieved improved precision in task of object detection on natural images, where objects of interests are annotated with horizontal boundary boxes. On aerial images captured from the bird-view perspective, these improvements on model architecture and deeper convolutional layers can also boost the performance on oriented object detection task. However, it is hard to directly apply those state-of-the-art object detectors on the devices with limited computation resources, which necessitates lightweight models through model …
