We propose a new model for detecting visual relationships, such as "person riding motorcycle" or "bottle on table". This task is an important step towards comprehensive structured image understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on three challenging datasets, V-COCO, Visual Relationships and Open Images, demonstrating strong quantitative and qualitative results.
Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost. Weakly-supervised methods, on the other hand, only require image-level labels for training, but the performance is far below their fully-supervised counterparts. In this paper, we propose a semi-supervised large scale fine-grained detectio…
We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-sta…
CNN is a powerful tool for many computer vision tasks, achieving much better result than traditional methods. Since CNN has a very large capacity, training such a neural network often requires many data, but it is often expensive to obtain labeled images in real practice, especially for object detection, where collecting bounding box of every object in training set requires many human efforts. This is the case in detection of retail products where there can be many different categories. In this paper, we focus on applying CNN to detect 324-categories products in situ, while requiring no extra …
Zhejiang University（浙江大学）；CVTE Research（CVTE研究院）；Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences（中国科学院西安光学精密机械研究所）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression. Regression plays a key role in the acquisition of bounding boxes in these methods, but it is not indispensable because text/non-text prediction can also be considered as a kind of semantic segmentation that contains full location information in itself. However, text instances in scene images often lie very close to each other, making them very difficult to separate via se…
Boston University（波士顿大学）；University of Washington（华盛顿大学）
While visual object detection with deep learning has received much attention in the past decade, cases when heavy intra-class occlusions occur have not been studied thoroughly. In this work, we propose a Non-Maximum-Suppression (NMS) algorithm that dramatically improves the detection recall while maintaining high precision in scenes with heavy occlusions. Our NMS algorithm is derived from a novel embedding mechanism, in which the semantic and geometric features of the detected boxes are jointly exploited. The embedding makes it possible to determine whether two heavily-overlapping boxes belong…
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；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）；Unit 31008 of the PLA（中国人民解放军31008部队）
Motivated by the development of deep convolution neural networks (DCNNs), tremendous progress has been gained in the field of aircraft detection. These DCNNs based detectors mainly belong to top-down approaches, which first enumerate massive potential locations of objects with the form of rectangular regions, and then identify whether they are objects or not. Compared with these top-down approaches, this paper shows that aircraft detection via bottom-up approach still performs competitively in the era of deep learning. We present a novel one-stage and anchor-free aircraft detection model in a …
We present Open Images V4, a dataset of 9.2M images with unified annotations for image classification, object detection and visual relationship detection. The images have a Creative Commons Attribution license that allows to share and adapt the material, and they have been collected from Flickr without a predefined list of class names or tags, leading to natural class statistics and avoiding an initial design bias. Open Images V4 offers large scale across several dimensions: 30.1M image-level labels for 19.8k concepts, 15.4M bounding boxes for 600 object classes, and 375k visual relationship a…
The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across multiple stages. Although modern instance segmentation cascades achieve leading performance, they mainly make use of a unidirectional relationship, i.e., mask segmentation can benefit from iteratively refined bounding box detection. In this paper, we investigate an alternative direction, i.e., how to take the advantage of precise mask segmentation for bounding box detection in a cascade architecture. We propose a Deeply…
Meta AI；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Current object detectors are limited in vocabulary size due to the small scale of detection datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as their datasets are larger and easier to collect. We propose Detic, which simply trains the classifiers of a detector on image classification data and thus expands the vocabulary of detectors to tens of thousands of concepts. Unlike prior work, Detic does not need complex assignment schemes to assign image labels to boxes based on model predictions, making it much easier to implement and compatible with a range of d…
Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone design for object detection. At the macro level, we propose Recursive Feature Pyramid, which incorporates extra feedback connections from Feature Pyramid Networks into the bottom-up backbone layers. At the micro level, we propose Switchable Atrous Convolution, which convolves the features with different atrous rates and gathers the results using switch functions. Combining them results in DetectoRS, which significantly …
Traditional neural objection detection methods use multi-scale features that allow multiple detectors to perform detecting tasks independently and in parallel. At the same time, with the handling of the prior box, the algorithm's ability to deal with scale invariance is enhanced. However, too many prior boxes and independent detectors will increase the computational redundancy of the detection algorithm. In this study, we introduce Dubox, a new one-stage approach that detects the objects without prior box. Working with multi-scale features, the designed dual scale residual unit makes dual scal…
In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles. Identifying and penalizing such riders is vital in curbing road accidents and improving citizens' safety. With this motivation, we propose an approach for detecting, tracking, and counting motorcycle riding violations in videos taken from a vehicle-mounted dashboard camera. We employ a curriculum learning-based object detector to better tackle challenging scenarios such as occlusions. We introduce a no…
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…
Universiti Teknologi Brunei（文莱达鲁萨兰大学）；National Institute of Information and Communications Technology（信息通信研究机构）；CLEALINKTECHNOLOGY Co., Ltd.（CLEALINK科技有限公司）
The ultimate goal of a baby detection task concerns detecting the presence of a baby and other objects in a sequence of 2D images, tracking them and understanding the semantic contents of the scene. Recent advances in deep learning and computer vision offer various powerful tools in general object detection and can be applied to a baby detection task. In this paper, the Faster Region-based Convolutional Neural Network and the Single-Shot Multi-Box Detection approaches are explored. They are the two state-of-the-art object detectors based on the region proposal tactic and the multi-box tactic. …
Large collections of geo-referenced panoramic images are freely available for cities across the globe, as well as detailed maps with location and meta-data on a great variety of urban objects. They provide a potentially rich source of information on urban objects, but manual annotation for object detection is costly, laborious and difficult. Can we utilize such multimedia sources to automatically annotate street level images as an inexpensive alternative to manual labeling? With the PanorAMS framework we introduce a method to automatically generate bounding box annotations for panoramic images…
University of Maryland, College Park（马里兰大学帕克分校）；NVIDIA（英伟达）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Caltech（加州理工学院）
We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision. Specifically, we propose a self-ensembling framework where instance segmentation and semantic correspondence are jointly guided by a structured teacher in addition to the bounding box supervision. The teacher is a structured energy model incorporating a pairwise potential and a cross-image potential to model the pairwise pixel relationships both within and across the boxes. Minimizing the teacher energy simultaneously yields refined object masks and den…
Noteheads are the interface between the written score and music. Each notehead on the page signifies one note to be played, and detecting noteheads is thus an unavoidable step for Optical Music Recognition. Noteheads are clearly distinct objects, however, the variety of music notation handwriting makes noteheads harder to identify, and while handwritten music notation symbol {\em classification} is a well-studied task, symbol {\em detection} has usually been limited to heuristics and rule-based systems instead of machine learning methods better suited to deal with the uncertainties in handwrit…
Adversarial patch attacks mislead neural networks by injecting adversarial pixels within a local region. Patch attacks can be highly effective in a variety of tasks and physically realizable via attachment (e.g. a sticker) to the real-world objects. Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images. We exploit this property and present PatchZero, a general defense pipeline against white-box adversarial patches without retraining the downstream classifier or detector. Specifically, our defense detects adversa…
Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task. Previous methods often treat this as a classification problem, considering each type of relationship (e.g. "ride") or each distinct visual phrase (e.g. "person-ride-horse") as a category. Such approaches are faced with significant difficulties caused by the high diversity of visual appearance for each kind of relationships or the large number of distinct visual…
To dynamically detect the facial landmarks in the video, we propose a novel hybrid framework termed as detection-tracking-detection (DTD). First, the face bounding box is achieved from the first frame of the video sequence based on a traditional face detection method. Then, a landmark detector detects the facial landmarks, which is based on a cascaded deep convolution neural network (DCNN). Next, the face bounding box in the current frame is estimated and validated after the facial landmarks in the previous frame are tracked based on the median flow. Finally, the facial landmarks in the curren…
Detecting visual relationships between people and clothing in an image has been a relatively unexplored problem in the field of computer vision and biometrics. The lack readily available public dataset for ``worn'' and ``unworn'' classification has slowed the development of solutions for this problem. We present the release of the Relatable Clothing Dataset which contains 35287 person-clothing pairs and segmentation masks for the development of ``worn'' and ``unworn'' classification models. Additionally, we propose a novel soft attention unit for performing ``worn'' and ``unworn'' classificati…
Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in current human detection benchmarks. In this paper, we introduce a new dataset, called CrowdHuman, to better evaluate detectors in crowd scenarios. The CrowdHuman dataset is large, rich-annotated and contains high diversity. There are a total of $470K$ human instances from the train and validation subsets, and $~22.6$ persons per image, with various kinds of occl…
Detecting small, densely distributed objects is a significant challenge: small objects often contain less distinctive information compared to larger ones, and finer-grained precision of bounding box boundaries are required. In this paper, we propose two techniques for addressing this problem. First, we estimate the likelihood that each pixel belongs to an object boundary rather than predicting coordinates of bounding boxes (as YOLO, Faster-RCNN and SSD do), by proposing a new architecture called Filter-Amplifier Networks (FANs). Second, we introduce a technique called Loss Boosting (LB) which …
Zongmu Technology（纵目科技）；Braunschweig University of Technology（不伦瑞克工业大学）
The owner-member relationship between wheels and vehicles contributes significantly to the 3D perception of vehicles, especially in embedded environments. However, to leverage this relationship we must face two major challenges: i) Traditional IoU-based heuristics have difficulty handling occluded traffic congestion scenarios. ii) The effectiveness and applicability of the solution in a vehicle-mounted system is difficult. To address these issues, we propose an innovative relationship prediction method, DeepWORD, by designing a graph convolutional network (GCN). Specifically, to improve the in…
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…
Oxford Brookes University（牛津布鲁克斯大学）；University of Oxford（牛津大学）
In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and motion detection networks are employed to localise and score actions from colour images and optical flow. In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial overlap. In stage 3, sequences of detection boxes most likely to be associated with a single action in…
Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial attacks (e.g., by checking the object co-occurrence relationships in complex scenes). However, existing approaches are tied to specific models and do not offer generalizability. Motivated by the observation that language descriptions of natural scene images have already captured the object co-occurrence relationships that can be learned by a language model, we dev…
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…
Most text detection methods hypothesize texts are horizontal or multi-oriented and thus define quadrangles as the basic detection unit. However, text in the wild is usually perspectively distorted or curved, which can not be easily tackled by existing approaches. In this paper, we propose a deep character embedding network (CENet) which simultaneously predicts the bounding boxes of characters and their embedding vectors, thus making text detection a simple clustering task in the character embedding space. The proposed method does not require strong assumptions of forming a straight line on gen…
Carnegie Mellon University（卡内基梅隆大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）
Visual relationship reasoning is a crucial yet challenging task for understanding rich interactions across visual concepts. For example, a relationship 'man, open, door' involves a complex relation 'open' between concrete entities 'man, door'. While much of the existing work has studied this problem in the context of still images, understanding visual relationships in videos has received limited attention. Due to their temporal nature, videos enable us to model and reason about a more comprehensive set of visual relationships, such as those requiring multiple (temporal) observations (e.g., 'ma…
University of California, San Diego（加州大学圣地亚哥分校）；Google Research（谷歌研究院）
We formulate the task of detecting lines and paragraphs in a document into a unified two-level clustering problem. Given a set of text detection boxes that roughly correspond to words, a text line is a cluster of boxes and a paragraph is a cluster of lines. These clusters form a two-level tree that represents a major part of the layout of a document. We use a graph convolutional network to predict the relations between text detection boxes and then build both levels of clusters from these predictions. Experimentally, we demonstrate that the unified approach can be highly efficient while still …
Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；University of California San Diego（加州大学圣地亚哥分校）；Intel Labs China（英特尔中国研究院）；Peking University（北京大学）
For humans, understanding the relationships between objects using visual signals is intuitive. For artificial intelligence, however, this task remains challenging. Researchers have made significant progress studying semantic relationship detection, such as human-object interaction detection and visual relationship detection. We take the study of visual relationships a step further from semantic to geometric. In specific, we predict relative occlusion and relative distance relationships. However, detecting these relationships from a single image is challenging. Enforcing focused attention to ta…
In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Region Proposal Network (RPN) to generate axis-aligned bounding boxes that enclose the texts with different orientations. Second, for each axis-aligned text box proposed by RPN, we extract its pooled features with different pooled sizes and the concatenated features are used to simultaneously predict the text/non-text score, axis-aligned box and inclined minimum area box. At last,…
In this work, we propose a novel approach that predicts the relationships between various entities in an image in a weakly supervised manner by relying on image captions and object bounding box annotations as the sole source of supervision. Our proposed approach uses a top-down attention mechanism to align entities in captions to objects in the image, and then leverage the syntactic structure of the captions to align the relations. We use these alignments to train a relation classification network, thereby obtaining both grounded captions and dense relationships. We demonstrate the effectivene…
Lesions characterized by computed tomography (CT) scans, are arguably often elliptical objects. However, current lesion detection systems are predominantly adopted from the popular Region Proposal Networks (RPNs) that only propose bounding boxes without fully leveraging the elliptical geometry of lesions. In this paper, we present Gaussian Proposal Networks (GPNs), a novel extension to RPNs, to detect lesion bounding ellipses. Instead of directly regressing the rotation angle of the ellipse as the common practice, GPN represents bounding ellipses as 2D Gaussian distributions on the image plain…
University of Chinese Academy of Sciences（中国科学院大学）；Beijing National Research Center for Information Science and Technology, Tsinghua University（北京信息科学与技术国家研究中心，清华大学）
School of Computing, National University of Singapore（新加坡国立大学计算学院）
We address the problem of Visual Relationship Detection (VRD) which aims to describe the relationships between pairs of objects in the form of triplets of (subject, predicate, object). We observe that given a pair of bounding box proposals, objects often participate in multiple relations implying the distribution of triplets is multimodal. We leverage the strong correlations within triplets to learn the joint distribution of triplet variables conditioned on the image and the bounding box proposals, doing away with the hitherto used independent distribution of triplets. To make learning the tri…
University of California, Davis（加州大学戴维斯分校）；University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）
We present a scalable approach for Detecting Objects by transferring Common-sense Knowledge (DOCK) from source to target categories. In our setting, the training data for the source categories have bounding box annotations, while those for the target categories only have image-level annotations. Current state-of-the-art approaches focus on image-level visual or semantic similarity to adapt a detector trained on the source categories to the new target categories. In contrast, our key idea is to (i) use similarity not at the image-level, but rather at the region-level, and (ii) leverage richer c…
Plant parasitic nematodes cause damage to crop plants on a global scale. Robust detection on image data is a prerequisite for monitoring such nematodes, as well as for many biological studies involving the nematode C. elegans, a common model organism. Here, we propose a framework for detecting worm-shaped objects in microscopic images that is based on convolutional neural networks (CNNs). We annotate nematodes with curved lines along the body, which is more suitable for worm-shaped objects than bounding boxes. The trained model predicts worm skeletons and body endpoints. The endpoints serve to…
The Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；University of Oxford（牛津大学）
We address the problem of detecting human-object interactions in images using graphical neural networks. Unlike conventional methods, where nodes send scaled but otherwise identical messages to each of their neighbours, we propose to condition messages between pairs of nodes on their spatial relationships, resulting in different messages going to neighbours of the same node. To this end, we explore various ways of applying spatial conditioning under a multi-branch structure. Through extensive experimentation we demonstrate the advantages of spatial conditioning for the computation of the adjac…
