With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent emerged task, layout-to-image, to learn generative models that are capable of synthesizing photo-realistic images from spatial layout (i.e., object bounding boxes configured in an image lattice) and style (i.e., structural and appearance variations encoded by latent vectors). This paper first proposes an intuitive paradigm for the task, layout-to-mask-to-image, to learn to unfold object masks of given bounding boxes in an input layout to bridge the gap between the input layout and synthesized images. Then, this paper presents a method built on Generative Adversarial Networks for the proposed layout-to-mask-to-image with style control at both image and mask levels. Object masks are learned from the input layout and iteratively refined along stages in the generator network. Style control at the image level is the same as in vanilla GANs, while style control at the object mask level is realized by a proposed novel feature normalization scheme, Instance-Sensitive and Layout-Aware Normalization. In experiments, the proposed method is tested in the COCO-Stuff dataset and the Visual Genome dataset with state-of-the-art performance obtained.
How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information. Recently, plenty of methods adopt the self-attention mechanisms to enhance the features in key frame with either global semantic information or local localization information. In this paper we introduce memory enhanced global-local aggregation (MEGA) network, which is among the first trials that takes full consideration of both global and local information. Furthermore, empowered by a novel and carefully-designed Long Range Memory (LRM) module, our proposed MEGA could enable the key frame to get access to much more content than any previous methods. Enhanced by these two sources of information, our method achieves state-of-the-art performance on ImageNet VID dataset. Code is available at \url{https://github.com/Scalsol/mega.pytorch}.
Existing techniques to encode spatial invariance within deep convolutional neural networks only model 2D transformation fields. This does not account for the fact that objects in a 2D space are a projection of 3D ones, and thus they have limited ability to severe object viewpoint changes. To overcome this limitation, we introduce a learnable module, cylindrical convolutional networks (CCNs), that exploit cylindrical representation of a convolutional kernel defined in the 3D space. CCNs extract a view-specific feature through a view-specific convolutional kernel to predict object category scores at each viewpoint. With the view-specific feature, we simultaneously determine objective category and viewpoints using the proposed sinusoidal soft-argmax module. Our experiments demonstrate the effectiveness of the cylindrical convolutional networks on joint object detection and viewpoint estimation.
Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of improved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant - requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks.
In this paper, we propose a novel real-time 6D object pose estimation framework, named G2L-Net. Our network operates on point clouds from RGB-D detection in a divide-and-conquer fashion. Specifically, our network consists of three steps. First, we extract the coarse object point cloud from the RGB-D image by 2D detection. Second, we feed the coarse object point cloud to a translation localization network to perform 3D segmentation and object translation prediction. Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation. In the third step, we define point-wise embedding vector features to capture viewpoint-aware information. To calculate more accurate rotation, we adopt a rotation residual estimator to estimate the residual between initial rotation and ground truth, which can boost initial pose estimation performance. Our proposed G2L-Net is real-time despite the fact multiple steps are stacked via the proposed coarse-to-fine framework. Extensive experiments on two benchmark datasets show that G2L-Net achieves state-of-the-art performance in terms of both accuracy and speed.
Video object segmentation (VOS) is a highly challenging problem, since the target object is only defined during inference with a given first-frame reference mask. The problem of how to capture and utilize this limited target information remains a fundamental research question. We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shot learning module. This internal learner is designed to predict a powerful parametric model of the target by minimizing a segmentation error in the first frame. We further go beyond standard few-shot learning techniques by learning what the few-shot learner should learn. This allows us to achieve a rich internal representation of the target in the current frame, significantly increasing the segmentation accuracy of our approach. We perform extensive experiments on multiple benchmarks. Our approach sets a new state-of-the-art on the large-scale YouTube-VOS 2018 dataset by achieving an overall score of 81.5, corresponding to a 2.6% relative improvement over the previous best result.
This paper presents a novel telepresence system for enhancing aerial manipulation capabilities. It involves not only a haptic device, but also a virtual reality that provides a 3D visual feedback to a remotely-located teleoperator in real-time. We achieve this by utilizing onboard visual and inertial sensors, an object tracking algorithm and a pre-generated object database. As the virtual reality has to closely match the real remote scene, we propose an extension of a marker tracking algorithm with visual-inertial odometry. Both indoor and outdoor experiments show benefits of our proposed system in achieving advanced aerial manipulation tasks, namely grasping, placing, force exertion and peg-in-hole insertion.
The task of detecting 3D objects is important to various robotic applications. The existing deep learning-based detection techniques have achieved impressive performance. However, these techniques are limited to run with a graphics processing unit (GPU) in a real-time environment. To achieve real-time 3D object detection with limited computational resources for robots, we propose an efficient detection method consisting of 3D proposal generation and classification. The proposal generation is mainly based on point segmentation, while the proposal classification is performed by a lightweight convolution neural network (CNN) model. To validate our method, KITTI datasets are utilized. The experimental results demonstrate the capability of proposed real-time 3D object detection method from the point cloud with a competitive performance of object recall and classification.
We explore the task of Video Object Grounding (VOG), which grounds objects in videos referred to in natural language descriptions. Previous methods apply image grounding based algorithms to address VOG, fail to explore the object relation information and suffer from limited generalization. Here, we investigate the role of object relations in VOG and propose a novel framework VOGNet to encode multi-modal object relations via self-attention with relative position encoding. To evaluate VOGNet, we propose novel contrasting sampling methods to generate more challenging grounding input samples, and construct a new dataset called ActivityNet-SRL (ASRL) based on existing caption and grounding datasets. Experiments on ASRL validate the need of encoding object relations in VOG, and our VOGNet outperforms competitive baselines by a significant margin.
Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since objects in natural visual scenes dynamically occlude and contain each-other. Intensive studies in developmental psychology suggest that object permanence is a challenging task that is learned through extensive experience. Here we introduce the setup of learning Object Permanence from data. We explain why this learning problem should be dissected into four components, where objects are (1) visible, (2) occluded, (3) contained by another object and (4) carried by a containing object. The fourth subtask, where a target object is carried by a containing object, is particularly challenging because it requires a system to reason about a moving location of an invisible object. We then present a unified deep architecture that learns to predict object location under these four scenarios. We evaluate the architecture and system on a new dataset based on CATER, and find that it outperforms previous localization methods and various baselines.
Consecutive frames in a video are highly redundant. Therefore, to perform the task of video object detection, executing single frame detectors on every frame without reusing any information is quite wasteful. It is with this idea in mind that we propose RN-VID (standing for RetinaNet-VIDeo), a novel approach to video object detection. Our contributions are twofold. First, we propose a new architecture that allows the usage of information from nearby frames to enhance feature maps. Second, we propose a novel module to merge feature maps of same dimensions using re-ordering of channels and 1 x 1 convolutions. We then demonstrate that RN-VID achieves better mean average precision (mAP) than corresponding single frame detectors with little additional cost during inference.
This work addresses the joint object discovery problem in videos while utilizing multiple object-related cues. In contrast to the usual spatial fusion approach, a novel appearance fusion approach is presented here. Specifically, this paper proposes an effective fusion process of different GMMs derived from multiple cues into one GMM. Much the same as any fusion strategy, this approach also needs some guidance. The proposed method relies on reliability and consensus phenomenon for guidance. As a case study, we pursue the "video co-localization" object discovery problem to propose our methodology. Our experiments on YouTube Objects and YouTube Co-localization datasets demonstrate that the proposed method of appearance fusion undoubtedly has an advantage over both the spatial fusion strategy and the current state-of-the-art video co-localization methods.
We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL apply to general multi-agent systems, and are expected to scale well to large systems.
This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise permutation invariant networks inspired from Deep Sets and gated-attention mechanisms. In a 2D procedurally-generated world where agents targeting goals in natural language navigate and interact with objects, we show that these architectures demonstrate strong generalization capacities to out-of-distribution goals. We study the generalization to varying numbers of objects at test time and further extend the object-centered architectures to goals involving relational reasoning.
Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly supervised object detection (WebSOD) method for novel classes which only requires the web images without further annotations. Our proposed method combines bottom-up and top-down cues for novel class detection. Within our approach, we introduce a bottom-up mechanism based on the well-trained fully supervised object detector (i.e. Faster RCNN) as an object region estimator for web images by recognizing the common objectiveness shared by base and novel classes. With the estimated regions on the web images, we then utilize the top-down attention cues as the guidance for region classification. Furthermore, we propose a residual feature refinement (RFR) block to tackle the domain mismatch between web domain and the target domain. We demonstrate our proposed method on PASCAL VOC dataset with three different novel/base splits. Without any target-domain novel-class images and annotations, our proposed webly supervised object detection model is able to achieve promising performance for novel classes. Moreover, we also conduct transfer learning experiments on large scale ILSVRC 2013 detection dataset and achieve state-of-the-art performance.
In this work, we present a new efficient method for convex shape representation, which is regardless of the dimension of the concerned objects, using level-set approaches. Convexity prior is very useful for object completion in computer vision. It is a very challenging task to design an efficient method for high dimensional convex objects representation. In this paper, we prove that the convexity of the considered object is equivalent to the convexity of the associated signed distance function. Then, the second order condition of convex functions is used to characterize the shape convexity equivalently. We apply this new method to two applications: object segmentation with convexity prior and convex hull problem (especially with outliers). For both applications, the involved problems can be written as a general optimization problem with three constraints. Efficient algorithm based on alternating direction method of multipliers is presented for the optimization problem. Numerical experiments are conducted to verify the effectiveness and efficiency of the proposed representation method and algorithm.
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods. The challenge focuses on multiple people tracking, since pedestrians are well studied in the tracking community, and precise tracking and detection has high practical relevance. Since the first release, MOT15, MOT16, and MOT17 have tremendously contributed to the community by introducing a clean dataset and precise framework to benchmark multi-object trackers. In this paper, we present our MOT20benchmark, consisting of 8 new sequences depicting very crowded challenging scenes. The benchmark was presented first at the 4thBMTT MOT Challenge Workshop at the Computer Vision and Pattern Recognition Conference (CVPR) 2019, and gives to chance to evaluate state-of-the-art methods for multiple object tracking when handling extremely crowded scenarios.
The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance. We propose an architecture with three components: ESRGAN, Edge Enhancement Network (EEN), and Detection network. We use residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we use the faster region-based convolutional network (FRCNN) (two-stage detector) and single-shot multi-box detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) and a self-assembled (oil and gas storage tank) satellite dataset show superior performance of our method compared to the standalone state-of-the-art object detectors.
A new paradigm is proposed for autonomous driving. The new paradigm lies between the end-to-end and pipelined approaches, and is inspired by how humans solve the problem. While it relies on scene understanding, the latter only considers objects that could originate hazard. These are denoted as action-inducing, since changes in their state should trigger vehicle actions. They also define a set of explanations for these actions, which should be produced jointly with the latter. An extension of the BDD100K dataset, annotated for a set of 4 actions and 21 explanations, is proposed. A new multi-task formulation of the problem, which optimizes the accuracy of both action commands and explanations, is then introduced. A CNN architecture is finally proposed to solve this problem, by combining reasoning about action inducing objects and global scene context. Experimental results show that the requirement of explanations improves the recognition of action-inducing objects, which in turn leads to better action predictions.
In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to eventually minimize the domain discrepancy. However, they still overlook to match crucial image regions and important instances across domains, which will strongly affect domain shift mitigation. In this work, we propose a simple but effective categorical regularization framework for alleviating this issue. It can be applied as a plug-and-play component on a series of Domain Adaptive Faster R-CNN methods which are prominent for dealing with domain adaptive detection. Specifically, by integrating an image-level multi-label classifier upon the detection backbone, we can obtain the sparse but crucial image regions corresponding to categorical information, thanks to the weakly localization ability of the classification manner. Meanwhile, at the instance level, we leverage the categorical consistency between image-level predictions (by the classifier) and instance-level predictions (by the detection head) as a regularization factor to automatically hunt for the hard aligned instances of target domains. Extensive experiments of various domain shift scenarios show that our method obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors. Furthermore, qualitative visualization and analyses can demonstrate the ability of our method for attending on the key regions/instances targeting on domain adaptation. Our code is open-source and available at \url{https://github.com/Megvii-Nanjing/CR-DA-DET}.