We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD). Motivated by the effectiveness of Masked Image Modeling (MIM), we propose Masked Bounding Box Reconstruction (MBBR), a variation of MIM where a percentage of the entities/objects within a scene are masked and subsequently reconstructed based on the unmasked objects. The core idea is that, through object-level masked modeling, the network learns context-aware representations that capture the interaction of objects within a scene and thus are highly predictive of visual object relationships. We extensively evaluate learned representations, both qualitatively and quantitatively, in a few-shot setting and demonstrate the efficacy of MBBR for learning robust visual representations, particularly tailored for VRD. The proposed method is able to surpass state-of-the-art VRD methods on the Predicate Detection (PredDet) evaluation setting, using only a few annotated samples. We make our code available at https://github.com/deeplab-ai/SelfSupervisedVRD.
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 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…
The development of high quality medical image segmentation algorithms depends on the availability of large datasets with pixel-level labels. The challenges of collecting such datasets, especially in case of 3D volumes, motivate to develop approaches that can learn from other types of labels that are cheap to obtain, e.g. bounding boxes. We focus on 3D medical images with their corresponding 3D bounding boxes which are considered as series of per-slice non-tight 2D bounding boxes. While current weakly-supervised approaches that use 2D bounding boxes as weak labels can be applied to medical imag…
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…
Ant Group（蚂蚁集团）；NetEase Fuxi AI Lab（网易伏羲人工智能实验室）；University of Rochester（罗切斯特大学）；Hangzhou Dianzi University（杭州电子科技大学）；Wuhan University（武汉大学）；Huazhong University of Science and Technology（华中科技大学）
Text detection and recognition are essential components of a modern OCR system. Most OCR approaches attempt to obtain accurate bounding boxes of text at the detection stage, which is used as the input of the text recognition stage. We observe that when using tight text bounding boxes as input, a text recognizer frequently fails to achieve optimal performance due to the inconsistency between bounding boxes and deep representations of text recognition. In this paper, we propose Box Adjuster, a reinforcement learning-based method for adjusting the shape of each text bounding box to make it more c…
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）
Training object class detectors typically requires a large set of images in which objects are annotated by bounding-boxes. However, manually drawing bounding-boxes is very time consuming. We propose a new scheme for training object detectors which only requires annotators to verify bounding-boxes produced automatically by the learning algorithm. Our scheme iterates between re-training the detector, re-localizing objects in the training images, and human verification. We use the verification signal both to improve re-training and to reduce the search space for re-localisation, which makes these…
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 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…
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…
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）
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…
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…
Huazhong University of Science and Technology（华中科技大学）；Worcester Polytechnic Institute（伍斯特理工学院）
Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. However, labeling such data is expensive and time-consuming. As the crowd-sourcing labeling process and the ambiguities of the objects may raise noisy bounding box annotations, the object detectors will suffer from the degenerated training data. In this work, we aim to address the challenge of learning robust object detectors with inaccurate bounding boxes. Inspired by the fact that localization precision suffers significantly from inaccurate bounding boxes while classification accur…
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…
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…
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 …
Ingenuity Labs Research Institute（Ingenuity Labs 研究院）
A novel object detection method is presented that handles freely rotated objects of arbitrary sizes, including tiny objects as small as $2\times 2$ pixels. Such tiny objects appear frequently in remotely sensed images, and present a challenge to recent object detection algorithms. More importantly, current object detection methods have been designed originally to accommodate axis-aligned bounding box detection, and therefore fail to accurately localize oriented boxes that best describe freely rotated objects. In contrast, the proposed CNN-based approach uses potential pixel information at mult…
We present a Deep Cuboid Detector which takes a consumer-quality RGB image of a cluttered scene and localizes all 3D cuboids (box-like objects). Contrary to classical approaches which fit a 3D model from low-level cues like corners, edges, and vanishing points, we propose an end-to-end deep learning system to detect cuboids across many semantic categories (e.g., ovens, shipping boxes, and furniture). We localize cuboids with a 2D bounding box, and simultaneously localize the cuboid's corners, effectively producing a 3D interpretation of box-like objects. We refine keypoints by pooling convolut…
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…
Rutgers University（罗格斯大学）；JD Digits（京东数字科技）；Lieber Institute for Brain Development（利伯大脑发育研究所）
Most existing methods handle cell instance segmentation problems directly without relying on additional detection boxes. These methods generally fails to separate touching cells due to the lack of global understanding of the objects. In contrast, box-based instance segmentation solves this problem by combining object detection with segmentation. However, existing methods typically utilize anchor box-based detectors, which would lead to inferior instance segmentation performance due to the class imbalance issue. In this paper, we propose a new box-based cell instance segmentation method. In par…
Cameras for traffic surveillance are usually pole-mounted and produce images that reflect a birds-eye view. Vehicles in such images, in general, assume an ellipse form. A bounding box for the vehicles usually includes a large empty space when the vehicle orientation is not parallel to the edges of the box. To circumvent this problem, the present study applied bounding ellipses to a non-anchor-based, single-shot detection model (CenterNet). Since this model does not depend on anchor boxes, non-max suppression (NMS) that requires computing the intersection over union (IOU) between predicted boun…
Object detection is a fundamental vision task. It has been highly researched in academia and has been widely adopted in industry. Average Precision (AP) is the standard score for evaluating object detectors. Our understanding of the subtleties of this score, however, is limited. Here, we quantify the sensitivity of AP to bounding box perturbations and show that AP is very sensitive to small translations. Only one pixel shift is enough to drop the mAP of a model by 8.4%. The mAP drop over small objects with only one pixel shift is 23.1%. The corresponding numbers when ground-truth (GT) boxes ar…
Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）
Detection of arbitrarily rotated objects is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects. In this article, a new detection method is proposed which applies the newly defined rotatable bounding box (RBox). The proposed detector (DRBox) can effectively handle the situation where the orientation angles of the objects are arbitrary. …
Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but they could be detrimental for learning. We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise. We propose a learning framework which jointly optimizes object labels, bounding box coordinates, and model parameters by performing alternating noise correcti…
Detection and tracking of vehicles captured by traffic surveillance cameras is a key component of intelligent transportation systems. We present an improved version of our algorithm for detection of 3D bounding boxes of vehicles, their tracking and subsequent speed estimation. Our algorithm utilizes the known geometry of vanishing points in the surveilled scene to construct a perspective transformation. The transformation enables an intuitive simplification of the problem of detecting 3D bounding boxes to detection of 2D bounding boxes with one additional parameter using a standard 2D object d…
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）
Imperial College London（帝国理工学院）；King’s College London（伦敦国王学院）；Hammersmith Hospital（哈默史密斯医院）
In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN …
In the majority of object detection frameworks, the confidence of instance classification is used as the quality criterion of predicted bounding boxes, like the confidence-based ranking in non-maximum suppression (NMS). However, the quality of bounding boxes, indicating the spatial relations, is not only correlated with the classification scores. Compared with the region proposal network (RPN) based detectors, single-shot object detectors suffer the box quality as there is a lack of pre-selection of box proposals. In this paper, we aim at single-shot object detectors and propose a location-awa…
Tohoku University（东北大学）；Riken Center for AIP（理化学研究所AIP中心）
We address a problem of estimating pose of a person's head from its RGB image. The employment of CNNs for the problem has contributed to significant improvement in accuracy in recent works. However, we show that the following two methods, despite their simplicity, can attain further improvement: (i) proper adjustment of the margin of bounding box of a detected face, and (ii) choice of loss functions. We show that the integration of these two methods achieve the new state-of-the-art on standard benchmark datasets for in-the-wild head pose estimation.
Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, the authors first predict high confidence detection results on the training set itself. Surprisingly, a considerable part of them exist in the same misalignment problem. Then, the authors carefully examine these cases and point out that annotation misalignment is the main reason. Later, a comprehensive di…
We present a method for 3D object detection and pose estimation from a single image. In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box. The first network output estimates the 3D object orientation using a novel hybrid discrete-continuous loss, which significantly outperforms the L2 loss. The second output regresses the …
University of Pittsburgh（匹兹堡大学）；The University of Melbourne（墨尔本大学）；Carnegie Mellon University（卡内基梅隆大学）
Deep learning has achieved remarkable success in medicalimage segmentation, but it usually requires a large numberof images labeled with fine-grained segmentation masks, andthe annotation of these masks can be very expensive andtime-consuming. Therefore, recent methods try to use un-supervised domain adaptation (UDA) methods to borrow in-formation from labeled data from other datasets (source do-mains) to a new dataset (target domain). However, due tothe absence of labels in the target domain, the performance ofUDA methods is much worse than that of the fully supervisedmethod. In this paper, w…
3D bounding boxes are a widespread intermediate representation in many computer vision applications. However, predicting them is a challenging task, largely due to partial observability, which motivates the need for a strong sense of uncertainty. While many recent methods have explored better architectures for consuming sparse and unstructured point cloud data, we hypothesize that there is room for improvement in the modeling of the output distribution and explore how this can be achieved using an autoregressive prediction head. Additionally, we release a simulated dataset, COB-3D, which highl…
Shanghai Jiao Tong University（上海交通大学）；Qing Yuan Research Institute（清源研究院）；Shanghai Qi Zhi Institute（上海期智研究院）
3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an additional Multi-Layer-Perceptron network. Both their offset and orientation predictions are not accurate due to the fundamental difficulty in rotation classification. In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations. Only LCC and box scales are regressed, while box orientations are …
We present a bottom-up approach for the task of object instance segmentation using a single-shot model. The proposed model employs a fully convolutional network which is trained to predict class-wise segmentation masks as well as the bounding boxes of the object instances to which each pixel belongs. This allows us to group object pixels into individual instances. Our network architecture is based on the DeepLabv3+ model, and requires only minimal extra computation to achieve pixel-wise instance assignments. We apply our method to the task of person instance segmentation, a common task relevan…
Harbin Institute of Technology（哈尔滨工业大学）；Tianjin University（天津大学）；Alibaba Group（阿里巴巴集团）；Pazhou Lab（琶洲实验室）
Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. However, the bounding boxes of most existing WSOD methods are mainly determined by precomputed proposals, thereby being limited in precise object localization. In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset. First, we use the well-annotated auxiliary dataset to explore a series of learnable bounding box adjusters (LBBAs) in a multi-…
OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）
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）
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 s…
Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent open vocabulary and zero-shot detection methods attempt to detect novel object categories beyond those seen during training. They achieve this goal by training on a pre-defined base categories to induce generalization to novel objects. However, their potential is still constrained by the small set of base categories available for training. To enlarge the set of…
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…
