Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking
Guangzhou Institute of Technology, Xidian University（西安电子科技大学广州研究院）；School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）计算机科学与技术学院）；School of Science, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）理学院）；School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院）；National Center for Applied Mathematics, Chongqing Normal University（重庆师范大学国家应用数学中心）
Di Yuan, Xiu Shu, Nana Fan, Xiaojun Chang, Qiao Liu, Zhenyu He
Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a maximum overlap method based on an intersection-over-union (IoU) loss to mitigate this problem, there are defects in the IoU loss itself, that make it impossible to continue to optimize the objective function when a given bounding box is completely contained within/without another bounding box; this makes it very challenging to accurately estimate the target state. Accordingly, in this paper, we address the above-mentioned problem by proposing a novel tracking method based on a distance-IoU (DIoU) loss, such that the proposed tracker consists of target estimation and target classification. The target estimation part is trained to predict the DIoU score between the target ground-truth bounding-box and the estimated bounding-box. The DIoU loss can maintain the advantage provided by the IoU loss while minimizing the distance between the center points of two bounding boxes, thereby making the target estimation more accurate. Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed. Comprehensive experimental results demonstrate that the proposed method achieves competitive tracking accuracy when compared to state-of-the-art trackers while with a real-time tracking speed.
Shanghai Jiao Tong University（上海交通大学）；Tencent AI Lab（腾讯AI实验室）
Adversarial attack arises due to the vulnerability of deep neural networks to perceive input samples injected with imperceptible perturbations. Recently, adversarial attack has been applied to visual object tracking to evaluate the robustness of deep trackers. Assuming that the model structures of deep trackers are known, a variety of white-box attack approaches to visual tracking have demonstrated promising results. However, the model knowledge about deep trackers is usually unavailable in real applications. In this paper, we propose a decision-based black-box attack method for visual object …
The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint detection and tracking method still suffers from high identity switches due to the inferior association method. To reduce the high number of identity switches and improve the tracking accuracy, in this paper, we propose to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm. Spec…
In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking. Our method, SiamMask_E, improves the bounding box fitting procedure of the state-of-the-art object tracking algorithm SiamMask and still retains a fast-tracking frame rate (80 fps) on a system equipped with GPU (GeForce GTX 1080 Ti or higher). We tested our approach on the visual object tracking datasets (VOT2016, VOT2018, and VOT2019) that were labeled with rotated bounding boxe…
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 …
Bounding box regression is the crucial step in object detection. In existing methods, while $\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training t…
School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；School of Computer Science, Fudan University（复旦大学计算机科学学院）
Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter $α$. We call this new family of losses the $α$-IoU losses and analyze properties such as order preservingness and loss/gradient reweighting. Experiments on multiple object detection benchmarks and models demo…
Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks
Beijing University of Technology（北京工业大学）；ShanghaiTech University（上海科技大学）；Beijing Institute of Technology（北京理工大学）；Beijing Electronic Science and Technology Institute（北京电子科技学院）；Zhengzhou University（郑州大学）；Yunnan Normal University（云南师范大学）
Alibaba Group（阿里巴巴集团）；Huazhong University of Science and Technology（华中科技大学）
Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem. We argue that the complex definition of IoU and feature misalignment make it difficult to predict IoU accurately. In this paper, we propose a novel Decoupled IoU …
Two-stage deep object detectors generate a set of regions-of-interest (RoI) in the first stage, then, in the second stage, identify objects among the proposed RoIs that sufficiently overlap with a ground truth (GT) box. The second stage is known to suffer from a bias towards RoIs that have low intersection-over-union (IoU) with the associated GT boxes. To address this issue, we first propose a sampling method to generate bounding boxes (BB) that overlap with a given reference box more than a given IoU threshold. Then, we use this BB generation method to develop a positive RoI (pRoI) generator …
University of Ostrava（俄斯特拉发大学）；Centre of Excellence IT4Innovations（IT4创新卓越中心）；Institute for Research and Applications of Fuzzy Modeling（模糊建模研究与应用研究所）
We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched space, and to reach a more precise approximation of the labels. The main principle is adding a smoothing part to the original IoU, where the smoothing part is given by a linear space with values that increases from the ground truth bounding box to the border of the input image, and thus covers the whole spatial search space. We show the motivation and forma…
Peking University（北京大学）；Megvii Inc. (Face++)（旷视科技（Face++））；Toutiao AI Lab（今日头条人工智能实验室）；Tsinghua University（清华大学）
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This makes properly localized bounding boxes degenerate during iterative regression or even suppressed during NMS. In the paper we propose IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth. The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bo…
Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-based loss has the gradient vanish problem in the case of low overlapping bounding boxes, and the model could easily ignore these simple cases. In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases. Besides, to speed up the convergence, the Corner Distance~(CD) is added into the objective function. Combining th…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Hangzhou Dianzi University（杭州电子科技大学）；Huawei Technologies Co., Ltd（华为技术有限公司）
As one of the most fundamental and challenging problems in computer vision, object detection tries to locate object instances and find their categories in natural images. The most important step in the evaluation of object detection algorithm is calculating the intersection-over-union (IoU) between the predicted bounding box and the ground truth one. Although this procedure is well-defined and solved for planar images, it is not easy for spherical image object detection. Existing methods either compute the IoUs based on biased bounding box representations or make excessive approximations, thus…
Numerous improvements for feedback mechanisms have contributed to the great progress in object detection. In this paper, we first present an evaluation-feedback module, which is proposed to consist of evaluation system and feedback mechanism. Then we analyze and summarize the disadvantages and improvements of traditional evaluation-feedback module. Finally, we focus on both the evaluation system and the feedback mechanism, and propose Control Distance IoU and Control Distance IoU loss function (or CDIoU and CDIoU loss for short) without increasing parameters or FLOPs in models, which show diff…
Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not consider the occluded region of the object and leads to improper training samples. To address such issue, a modification called visible IoU is proposed in this paper to explicitly incorporate the visible ratio in selecting samples. Then a newly designed box sign predictor is placed in parallel with box regressor to separately predict the moving direction of training samples. It leads to higher localization accuracy …
CASIA（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Horizon Robotics（地平线机器人）
In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. However, we find that most previous loss functions for BBR have two main drawbacks: (i) Both $\ell_n$-norm and IOU-based loss functions are inefficient to depict the objective of BBR, which leads to slow convergence and inaccurate regression results. (ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR. To mitigate the adverse effec…
University of New England（新英格兰大学）；Flinders University（弗林德斯大学）；Melbourne Institute of Technology（墨尔本理工学院）
Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more stable, consistent predictor of bounding box clustering by using a normalized Manhattan Distance inspired proximity metric to represent bounding box clustering. Unlike Greedy and Soft NMS, it does not rely solely on classification confidence scores to select optimal bounding boxes, instead selecting the box which is closest to every other box within a given clust…
The most popular evaluation metric for object detection in 2D images is Intersection over Union (IoU). Existing implementations of the IoU metric for 3D object detection usually neglect one or more degrees of freedom. In this paper, we first derive the analytic solution for three dimensional bounding boxes. As a second contribution, a closed-form solution of the volume-to-volume distance is derived. Finally, the Bounding Box Disparity is proposed as a combined positive continuous metric. We provide open source implementations of the three metrics as standalone python functions, as well as exte…
Stanford University（斯坦福大学）；The University of Adelaide（阿德莱德大学）；Aibee Inc（Aibee公司）
Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself. In the case of axis-aligned 2D bounding boxes, it can be shown that $IoU$ can be directly used as a regression loss. However, $IoU$ has a plateau making it infeasible to optimize in the case of non-overlapping bounding boxes. In this paper, we address the weaknesses of $IoU$…
IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models
University of Chinese Academy of Sciences（中国科学院大学）；State Key Laboratory of Communication Content Cognition（通信内容认知技术国家重点实验室）；Peng Cheng Laboratory（鹏城实验室）
School of Automation Science and Electrical Engineering, Beihang University（北京航空航天大学自动化科学与电气工程学院）；Institute of Unmanned System, Beihang University（北京航空航天大学无人系统研究院）
We demonstrate that many detection methods are designed to identify only a sufficently accurate bounding box, rather than the best available one. To address this issue we propose a simple and fast modification to the existing methods called Fitness NMS. This method is tested with the DeNet model and obtains a significantly improved MAP at greater localization accuracies without a loss in evaluation rate, and can be used in conjunction with Soft NMS for additional improvements. Next we derive a novel bounding box regression loss based on a set of IoU upper bounds that better matches the goal of…
Tokyo Institute of Technology（东京工业大学）；NTT Corporation（日本电报电话公司）
The combined use of multiple modalities enables accurate pedestrian detection under poor lighting conditions by using the high visibility areas from these modalities together. The vital assumption for the combination use is that there is no or only a weak misalignment between the two modalities. In general, however, this assumption often breaks in actual situations. Due to this assumption's breakdown, the position of the bounding boxes does not match between the two modalities, resulting in a significant decrease in detection accuracy, especially in regions where the amount of misalignment is …
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 …
Bounding-box regression is a popular technique to refine or predict localization boxes in recent object detection approaches. Typically, bounding-box regressors are trained to regress from either region proposals or fixed anchor boxes to nearby bounding boxes of a pre-defined target object classes. This paper investigates whether the technique is generalizable to unseen classes and is transferable to other tasks beyond supervised object detection. To this end, we propose a class-agnostic and anchor-free box regressor, dubbed Universal Bounding-Box Regressor (UBBR), which predicts a bounding bo…
Horizon Med Innovation, Inc.（Horizon Med创新公司）；Shenzhen SiBright Co., Ltd.（深圳思博瑞特有限公司）
Weakly supervised image segmentation approaches in the literature usually achieve high segmentation performance using tight bounding box supervision and decrease the performance greatly when supervised by loose bounding boxes. However, compared with loose bounding box, it is much more difficult to acquire tight bounding box due to its strict requirements on the precise locations of the four sides of the box. To resolve this issue, this study investigates whether it is possible to maintain good segmentation performance when loose bounding boxes are used as supervision. For this purpose, this wo…
Zhejiang University（浙江大学）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；IIAI
Most existing point cloud based 3D object detectors focus on the tasks of classification and box regression. However, another bottleneck in this area is achieving an accurate detection confidence for the Non-Maximum Suppression (NMS) post-processing. In this paper, we add a 3D IoU prediction branch to the regular classification and regression branches. The predicted IoU is used as the detection confidence for NMS. In order to obtain a more accurate IoU prediction, we propose a 3D IoU-Net with IoU sensitive feature learning and an IoU alignment operation. To obtain a perspective-invariant predi…
Carnegie Mellon University（卡内基梅隆大学）；Megvii Inc. (Face++)（旷视科技（Face++））
Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. However, we observe that ambiguities are still introduced when labeling the bounding boxes. In this paper, we propose a novel bounding box regression loss for learning bounding box transformation and localization variance together. Our loss greatly improves the localization accuracies of various architectures with nearly no additional computation. The learned localization variance allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which furt…
BSN iNet Co. Ltd.（BSN iNet有限公司）；Tokyo National Museum（东京国立博物馆）
Detection performances on bounding box and segmentation mask outputs of Mask R-CNN models are evaluated. There are significant differences in detection performances of bounding boxes and segmentation masks, where the former is constantly superior to the latter. Harmonic values of precisions and recalls of linear cracks, joints, fillings, and shadows are significantly lower in segmentation masks than bounding boxes. Other classes showed similar harmonic values. Discussions are made on different performances of detection metrics of bounding boxes and segmentation masks focusing on detection algo…
Technical University of Munich（慕尼黑工业大学）；Artisense（Artisense公司）
The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling. We propose a network architecture and training procedure for learning monocular 3D object detection without 3D bounding box labels. By representing the objects as triangular meshes and employing differentiable shape rendering, we define loss functions based on depth maps, segmentation masks, and ego- and object-motion, which are generated by pre-trained, off-the-shelf networks. We evaluate the proposed algorithm on the real-worl…
University of Luebeck（吕贝克大学）；Birla Institute of Technology and Science, Pilani（皮拉尼伯拉理工学院）
The size of an individual cell type, such as a red blood cell, does not vary much among humans. We use this knowledge as a prior for classifying and detecting cells in images with only a few ground truth bounding box annotations, while most of the cells are annotated with points. This setting leads to weakly semi-supervised learning. We propose replacing points with either stochastic (ST) boxes or bounding box predictions during the training process. The proposed "mean-IOU" ST box maximizes the overlap with all the boxes belonging to the sample space with a class-specific approximated prior pr…
Sketchy Bounding-box Supervision for 3D Instance Segmentation
PCA Lab, College of Computer Science, Nankai University（南开大学计算机科学学院PCA实验室）；School of Electronics and Information, Northwestern Polytechnical University（西北工业大学电子与信息学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
We approach video object segmentation (VOS) by splitting the task into two sub-tasks: bounding box level tracking, followed by bounding box segmentation. Following this paradigm, we present BoLTVOS (Box-Level Tracking for VOS), which consists of an R-CNN detector conditioned on the first-frame bounding box to detect the object of interest, a temporal consistency rescoring algorithm, and a Box2Seg network that converts bounding boxes to segmentation masks. BoLTVOS performs VOS using only the firstframe bounding box without the mask. We evaluate our approach on DAVIS 2017 and YouTube-VOS, and sh…
DFKI - German Research Center for Artificial Intelligence（德国人工智能研究中心）
We present a new, simple yet effective approach to uplift video object detection. We observe that prior works operate on instance-level feature aggregation that imminently neglects the refined pixel-level representation, resulting in confusion among objects sharing similar appearance or motion characteristics. To address this limitation, we propose BoxMask, which effectively learns discriminative representations by incorporating class-aware pixel-level information. We simply consider bounding box-level annotations as a coarse mask for each object to supervise our method. The proposed module ca…
In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods. Specifically, we perform the network feed-forwarding in a bottom-up manner, and then parse the poses with bounding box constraints in a top-down manner. In contrast to the previous top-down methods, our method is robust to bounding box shift and tightness. We extract features from an original image by a residual network and train the network to learn both the confidence maps of joints and the connection relationships between joints. During testing, the predi…
LG Canada（LG加拿大）；Huawei Technologies Canada（华为技术加拿大）
We present a learning-based method to estimate the object bounding box from its 2D bird's-eye view (BEV) LiDAR points. Our method, entitled BoxNet, exploits a simple deep neural network that can efficiently handle unordered points. The method takes as input the 2D coordinates of all the points and the output is a vector consisting of both the box pose (position and orientation in LiDAR coordinate system) and its size (width and length). In order to deal with the angle discontinuity problem, we propose to estimate the double-angle sinusoidal values rather than the angle itself. We also predict …
In this paper, we present a simple but powerful method to tackle the problem of estimating the 6D pose of objects from a single RGB image. Our system trains a novel convolutional neural network to regress the unit quaternion, which represents the 3D rotation, from the partial image inside the bounding box returned by 2D detection systems. Then we propose an algorithm we call Bounding Box Equation to efficiently and accurately obtain the 3D translation, using 3D rotation and 2D bounding box. Considering that the quadratic sum of the quaternion's four elements equals to one, we add a normalizati…
The existing Optical Character Recognition (OCR) systems are capable of recognizing images with horizontal texts. However, when the rotation of the texts increases, it becomes harder to recognizing these texts. The performance of the OCR systems decreases. Thus predicting the rotations of the texts and correcting the images are important. Previous work mainly uses traditional Computer Vision methods like Hough Transform and Deep Learning methods like Convolutional Neural Network. However, all of these methods are prone to background noises commonly existing in general images with texts. To tac…
Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
The Australian National University（澳大利亚国立大学）；OpenGVLab（开放视觉实验室）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Nanjing University（南京大学）；Tsinghua University（清华大学）
EPFL（洛桑联邦理工学院）；Google AI Perception（谷歌人工智能感知部）；IST Austria（奥地利科学技术研究所）
We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider two actions: box verification, where the annotator verifies a box generated by an object detector, and manual box drawing. We explore two kinds of agents, one based on predicting the probability that a box will be positively verified, and the other based on reinforcement learning. We demonstrate that (1) our agents are able to learn efficient annotation stra…
Seoul National University（首尔大学）；ASRI（先进技术研究中心）；INMC（纳米材料与技术研究所）；ISRC（智能系统研究中心）；Institute of Engineering Research（工程研究院）
Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the low-level information intrinsic to an image. In this work, we utilize higher-level information from the behavior of a trained object detector, by seeking the smallest areas of the image from which the object detector produces almost the same result as it does from the whole image. These areas constitute a bounding-box attribution map (BBAM), which identifies the…
Video and Image Processing Laboratory (VIPER), Purdue University（普渡大学视频与图像处理实验室（VIPER），普渡大学）
Recent advances in convolutional neural networks (CNN) have achieved remarkable results in locating objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any fully convolutional network (FCN) to estimate object locations. This loss function is a modification of the average Hausdorff distance between t…
Seoul National University（首尔大学）；Samsung Advanced Institute of Technology（三星综合技术院）
In multi-object detection using neural networks, the fundamental problem is, "How should the network learn a variable number of bounding boxes in different input images?". Previous methods train a multi-object detection network through a procedure that directly assigns the ground truth bounding boxes to the specific locations of the network's output. However, this procedure makes the training of a multi-object detection network too heuristic and complicated. In this paper, we reformulate the multi-object detection task as a problem of density estimation of bounding boxes. Instead of assigning …
