Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level annotations indirectly. In this paper, we demonstrate that weakly supervised object localization should be divided into two parts: class-agnostic object localization and object classification. For class-agnostic object localization, we should use class-agnostic methods to generate noisy pseudo annotations and then perform bounding box regression on them without class labels. We propose the pseudo supervised object localization (PSOL) method as a new way to solve WSOL. Our PSOL models have good transferability across different datasets without fine-tuning. With generated pseudo bounding boxes, we achieve 58.00% localization accuracy on ImageNet and 74.97% localization accuracy on CUB-200, which have a large edge over previous models.
Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird's eye view evaluation. The code will be made publicly available.
We present BlockGAN, an image generative model that learns object-aware 3D scene representations directly from unlabelled 2D images. Current work on scene representation learning either ignores scene background or treats the whole scene as one object. Meanwhile, work that considers scene compositionality treats scene objects only as image patches or 2D layers with alpha maps. Inspired by the computer graphics pipeline, we design BlockGAN to learn to first generate 3D features of background and foreground objects, then combine them into 3D features for the wholes cene, and finally render them into realistic images. This allows BlockGAN to reason over occlusion and interaction between objects' appearance, such as shadow and lighting, and provides control over each object's 3D pose and identity, while maintaining image realism. BlockGAN is trained end-to-end, using only unlabelled single images, without the need for 3D geometry, pose labels, object masks, or multiple views of the same scene. Our experiments show that using explicit 3D features to represent objects allows BlockGAN to learn disentangled representations both in terms of objects (foreground and background) and their properties (pose and identity).
Most state of the art object detectors output multiple detections per object. The duplicates are removed in a post-processing step called Non-Maximum Suppression. Classical Non-Maximum Suppression has shortcomings in scenes that contain objects with high overlap: This heuristic assumes that a high overlap between two bounding boxes corresponds to a high probability of one being a duplicate. We propose FeatureNMS to solve this problem. FeatureNMS recognizes duplicates not only based on the intersection over union between the bounding boxes, but also based on the difference of feature vectors. These feature vectors can encode more information like visual appearance. Our approach outperforms classical NMS and derived approaches and achieves state of the art performance.
Instance segmentation is an important task for biomedical and biological image analysis. Due to the complicated background components, the high variability of object appearances, numerous overlapping objects, and ambiguous object boundaries, this task still remains challenging. Recently, deep learning based methods have been widely employed to solve these problems and can be categorized into proposal-free and proposal-based methods. However, both proposal-free and proposal-based methods suffer from information loss, as they focus on either global-level semantic or local-level instance features. To tackle this issue, we present a Panoptic Feature Fusion Net (PFFNet) that unifies the semantic and instance features in this work. Specifically, our proposed PFFNet contains a residual attention feature fusion mechanism to incorporate the instance prediction with the semantic features, in order to facilitate the semantic contextual information learning in the instance branch. Then, a mask quality sub-branch is designed to align the confidence score of each object with the quality of the mask prediction. Furthermore, a consistency regularization mechanism is designed between the semantic segmentation tasks in the semantic and instance branches, for the robust learning of both tasks. Extensive experiments demonstrate the effectiveness of our proposed PFFNet, which outperforms several state-of-the-art methods on various biomedical and biological datasets.
This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this problem has proposed to use soft sampling to re-weight the gradients of RoIs based on the overlaps with positive instances, while their method is mainly based on the two-stage detector (i.e. Faster RCNN) which is more robust and friendly for the missing label scenario. In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image. Our design is built on the one-stage detector which is faster and lighter. Inspired by the Focal Loss formulation, we make several significant modifications to fit on the missing-annotation circumstance. We conduct extensive experiments on the curated PASCAL VOC and MS COCO datasets. The results demonstrate that our proposed method outperforms the baseline and other state-of-the-arts by a large margin. Code available: https://github.com/Dwrety/mmdetection-selective-iou.
Humans are very good at directing their visual attention toward relevant areas when they search for different types of objects. For instance, when we search for cars, we will look at the streets, not at the top of buildings. The motivation of this paper is to train a network to do the same via a multi-task learning approach. To train visual attention, we produce foreground/background segmentation labels in a semi-supervised way, using background subtraction or optical flow. Using these labels, we train an object detection model to produce foreground/background segmentation maps as well as bounding boxes while sharing most model parameters. We use those segmentation maps inside the network as a self-attention mechanism to weight the feature map used to produce the bounding boxes, decreasing the signal of non-relevant areas. We show that by using this method, we obtain a significant mAP improvement on two traffic surveillance datasets, with state-of-the-art results on both UA-DETRAC and UAVDT.
The state-of-the-art deep neural networks (DNNs) are vulnerable against adversarial examples with additive random-like noise perturbations. While such examples are hardly found in the physical world, the image blurring effect caused by object motion, on the other hand, commonly occurs in practice, making the study of which greatly important especially for the widely adopted real-time image processing tasks (e.g., object detection, tracking). In this paper, we initiate the first step to comprehensively investigate the potential hazards of the blur effect for DNN, caused by object motion. We propose a novel adversarial attack method that can generate visually natural motion-blurred adversarial examples, named motion-based adversarial blur attack (ABBA). To this end, we first formulate the kernel-prediction-based attack where an input image is convolved with kernels in a pixel-wise way, and the misclassification capability is achieved by tuning the kernel weights. To generate visually more natural and plausible examples, we further propose the saliency-regularized adversarial kernel prediction, where the salient region serves as a moving object, and the predicted kernel is regularized to achieve naturally visual effects. Besides, the attack is further enhanced by adaptively tuning the translations of object and background. A comprehensive evaluation on the NeurIPS'17 adversarial competition dataset demonstrates the effectiveness of ABBA by considering various kernel sizes, translations, and regions. The in-depth study further confirms that our method shows more effective penetrating capability to the state-of-the-art GAN-based deblurring mechanisms compared with other blurring methods. We release the code to https://github.com/tsingqguo/ABBA.
Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years. Existing approaches using multiple instance learning easily fall into local optima, because such mechanism tends to learn from the most discriminative object in an image for each category. Therefore, these methods suffer from missing object instances which degrade the performance of WSOD. To address this problem, this paper introduces an end-to-end object instance mining (OIM) framework for weakly supervised object detection. OIM attempts to detect all possible object instances existing in each image by introducing information propagation on the spatial and appearance graphs, without any additional annotations. During the iterative learning process, the less discriminative object instances from the same class can be gradually detected and utilized for training. In addition, we design an object instance reweighted loss to learn larger portion of each object instance to further improve the performance. The experimental results on two publicly available databases, VOC 2007 and 2012, demonstrate the efficacy of proposed approach.
We developed a real-time, high-quality semi-supervised video object segmentation algorithm. Its accuracy is on par with the most accurate, time-consuming online-learning model, while its speed is similar to the fastest template-matching method with sub-optimal accuracy. The core component of the model is a novel global context module that effectively summarizes and propagates information through the entire video. Compared to previous approaches that only use one frame or a few frames to guide the segmentation of the current frame, the global context module uses all past frames. Unlike the previous state-of-the-art space-time memory network that caches a memory at each spatio-temporal position, the global context module uses a fixed-size feature representation. Therefore, it uses constant memory regardless of the video length and costs substantially less memory and computation. With the novel module, our model achieves top performance on standard benchmarks at a real-time speed.
This paper addresses the task of estimating the 6 degrees of freedom pose of a known 3D object from depth information represented by a point cloud. Deep features learned by convolutional neural networks from color information have been the dominant features to be used for inferring object poses, while depth information receives much less attention. However, depth information contains rich geometric information of the object shape, which is important for inferring the object pose. We use depth information represented by point clouds as the input to both deep networks and geometry-based pose refinement and use separate networks for rotation and translation regression. We argue that the axis-angle representation is a suitable rotation representation for deep learning, and use a geodesic loss function for rotation regression. Ablation studies show that these design choices outperform alternatives such as the quaternion representation and L2 loss, or regressing translation and rotation with the same network. Our simple yet effective approach clearly outperforms state-of-the-art methods on the YCB-video dataset. The implementation and trained model are avaliable at: https://github.com/GeeeG/CloudPose.
In this paper, we consider a novel task, Spatio-Temporal Video Grounding for Multi-Form Sentences (STVG). Given an untrimmed video and a declarative/interrogative sentence depicting an object, STVG aims to localize the spatio-temporal tube of the queried object. STVG has two challenging settings: (1) We need to localize spatio-temporal object tubes from untrimmed videos, where the object may only exist in a very small segment of the video; (2) We deal with multi-form sentences, including the declarative sentences with explicit objects and interrogative sentences with unknown objects. Existing methods cannot tackle the STVG task due to the ineffective tube pre-generation and the lack of object relationship modeling. Thus, we then propose a novel Spatio-Temporal Graph Reasoning Network (STGRN) for this task. First, we build a spatio-temporal region graph to capture the region relationships with temporal object dynamics, which involves the implicit and explicit spatial subgraphs in each frame and the temporal dynamic subgraph across frames. We then incorporate textual clues into the graph and develop the multi-step cross-modal graph reasoning. Next, we introduce a spatio-temporal localizer with a dynamic selection method to directly retrieve the spatio-temporal tubes without tube pre-generation. Moreover, we contribute a large-scale video grounding dataset VidSTG based on video relation dataset VidOR. The extensive experiments demonstrate the effectiveness of our method.
Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal WSOL work of class activation mapping (CAM), the field has focused on how to expand the attention regions to cover objects more broadly and localize them better. However, these strategies rely on full localization supervision to validate hyperparameters and for model selection, which is in principle prohibited under the WSOL setup. In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set. We observe that, under our protocol, the five most recent WSOL methods have not made a major improvement over the CAM baseline. Moreover, we report that existing WSOL methods have not reached the few-shot learning baseline, where the full-supervision at validation time is used for model training instead. Based on our findings, we discuss some future directions for WSOL.
Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset.
Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual worlds. In this work, we focus on predicting the dynamics of 3D objects on a plane that have just been subjected to an impulsive force. In particular, we predict the changes in state - 3D position, rotation, velocities, and stability. Different from previous work, our approach can generalize dynamics predictions to object shapes and initial conditions that were unseen during training. Our method takes the 3D object's shape as a point cloud and its initial linear and angular velocities as input. We extract shape features and use a recurrent neural network to predict the full change in state at each time step. Our model can support training with data from both a physics engine or the real world. Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.
3D multi-object tracking is a key module in autonomous driving applications that provides a reliable dynamic representation of the world to the planning module. In this paper, we present our on-line tracking method, which made the first place in the NuScenes Tracking Challenge, held at the AI Driving Olympics Workshop at NeurIPS 2019. Our method estimates the object states by adopting a Kalman Filter. We initialize the state covariance as well as the process and observation noise covariance with statistics from the training set. We also use the stochastic information from the Kalman Filter in the data association step by measuring the Mahalanobis distance between the predicted object states and current object detections. Our experimental results on the NuScenes validation and test set show that our method outperforms the AB3DMOT baseline method by a large margin in the Average Multi-Object Tracking Accuracy (AMOTA) metric.
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors because there is a large performance gap between image-based and LiDAR-based methods. It is caused by the way to form representation for the prediction in 3D scenarios. Our method, called Deep Stereo Geometry Network (DSGN), significantly reduces this gap by detecting 3D objects on a differentiable volumetric representation -- 3D geometric volume, which effectively encodes 3D geometric structure for 3D regular space. With this representation, we learn depth information and semantic cues simultaneously. For the first time, we provide a simple and effective one-stage stereo-based 3D detection pipeline that jointly estimates the depth and detects 3D objects in an end-to-end learning manner. Our approach outperforms previous stereo-based 3D detectors (about 10 higher in terms of AP) and even achieves comparable performance with several LiDAR-based methods on the KITTI 3D object detection leaderboard. Our code is publicly available at https://github.com/chenyilun95/DSGN.
We present MatrixNets (xNets), a new deep architecture for object detection. xNets map objects with similar sizes and aspect ratios into many specialized layers, allowing xNets to provide a scale and aspect ratio aware architecture. We leverage xNets to enhance single-stage object detection frameworks. First, we apply xNets on anchor-based object detection, for which we predict object centers and regress the top-left and bottom-right corners. Second, we use MatrixNets for corner-based object detection by predicting top-left and bottom-right corners. Each corner predicts the center location of the object. We also enhance corner-based detection by replacing the embedding layer with center regression. Our final architecture achieves mAP of 47.8 on MS COCO, which is higher than its CornerNet counterpart by +5.6 mAP while also closing the gap between single-stage and two-stage detectors. The code is available at https://github.com/arashwan/matrixnet.
We present an algorithm to generate diverse foreground objects and composite them into background images using a GAN architecture. Given an object class, a user-provided bounding box, and a background image, we first use a mask generator to create an object shape, and then use a texture generator to fill the mask such that the texture integrates with the background. By separating the problem of object insertion into these two stages, we show that our model allows us to improve the realism of diverse object generation that also agrees with the provided background image. Our results on the challenging COCO dataset show improved overall quality and diversity compared to state-of-the-art object insertion approaches.
In scene understanding, robotics benefit from not only detecting individual scene instances but also from learning their possible interactions. Human-Object Interaction (HOI) Detection infers the action predicate on a <human, predicate, object> triplet. Contextual information has been found critical in inferring interactions. However, most works only use local features from single human-object pair for inference. Few works have studied the disambiguating contribution of subsidiary relations made available via graph networks. Similarly, few have learned to effectively leverage visual cues along with the intrinsic semantic regularities contained in HOIs. We contribute a dual-graph attention network that effectively aggregates contextual visual, spatial, and semantic information dynamically from primary human-object relations as well as subsidiary relations through attention mechanisms for strong disambiguating power. We achieve comparable results on two benchmarks: V-COCO and HICO-DET. Code is available at \url{https://github.com/birlrobotics/vs-gats}.