We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-proposal relations, providing higher-level feature learning in addition to the lower-level point features. Each proposal comprises a semantic label, a set of associated points over which we define a foreground-background mask, an objectness score and aggregation features. Previous works usually perform non-maximum-suppression (NMS) over proposals to obtain the final object detections or semantic instances. However, NMS can discard potentially correct predictions. Instead, our approach keeps all proposals and groups them together based on the learned aggregation features. We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.
Understanding interactions between humans and objects is one of the fundamental problems in visual classification and an essential step towards detailed scene understanding. Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them. Most existing HOI detection approaches are instance-centric where interactions between all possible human-object pairs are predicted based on appearance features and coarse spatial information. We argue that appearance features alone are insufficient to capture complex human-object interactions. In this paper, we therefore propose a novel fully-convolutional approach that directly detects the interactions between human-object pairs. Our network predicts interaction points, which directly localize and classify the inter-action. Paired with the densely predicted interaction vectors, the interactions are associated with human and object detections to obtain final predictions. To the best of our knowledge, we are the first to propose an approach where HOI detection is posed as a keypoint detection and grouping problem. Experiments are performed on two popular benchmarks: V-COCO and HICO-DET. Our approach sets a new state-of-the-art on both datasets. Code is available at https://github.com/vaesl/IP-Net.
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
Visual attention brings significant progress for Convolution Neural Networks (CNNs) in various applications. In this paper, object-based attention in human visual cortex inspires us to introduce a mechanism for modification of activations in feature maps of CNNs. In this mechanism, the activations of object locations are excited in feature maps. This mechanism is specifically inspired by attention-based gain modulation in object-based attention in brain. It facilitates figure-ground segregation in the visual cortex. Similar to brain, we use the idea to address two challenges in salient object detection: gathering object interior parts while segregation from background with concise boundaries. We implement the object-based attention in the U-net model using different architectures in the encoder parts, including AlexNet, VGG, and ResNet. The proposed method was examined on three benchmark datasets: HKU-IS, MSRB, and PASCAL-S. Experimental results showed that our inspired method could significantly improve the results in terms of mean absolute error and F-measure. The results also showed that our proposed method better captured not only the boundary but also the object interior. Thus, it can tackle the mentioned challenges.
Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: https://github.com/JDAI-CV/LIO.
It has been well recognized that modeling human-object or object-object relations would be helpful for detection task. Nevertheless, the problem is not trivial especially when exploring the interactions between human actor, object and scene (collectively as human-context) to boost video action detectors. The difficulty originates from the aspect that reliable relations in a video should depend on not only short-term human-context relation in the present clip but also the temporal dynamics distilled over a long-range span of the video. This motivates us to capture both short-term and long-term relations in a video. In this paper, we present a new Long Short-Term Relation Networks, dubbed as LSTR, that novelly aggregates and propagates relation to augment features for video action detection. Technically, Region Proposal Networks (RPN) is remoulded to first produce 3D bounding boxes, i.e., tubelets, in each video clip. LSTR then models short-term human-context interactions within each clip through spatio-temporal attention mechanism and reasons long-term temporal dynamics across video clips via Graph Convolutional Networks (GCN) in a cascaded manner. Extensive experiments are conducted on four benchmark datasets, and superior results are reported when comparing to state-of-the-art methods.
Local and global patterns of an object are closely related. Although each part of an object is incomplete, the underlying attributes about the object are shared among all parts, which makes reasoning the whole object from a single part possible. We hypothesize that a powerful representation of a 3D object should model the attributes that are shared between parts and the whole object, and distinguishable from other objects. Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision. Experimental results on various benchmark datasets demonstrate the unsupervisedly learned representation is even better than supervised representation in discriminative power, generalization ability, and robustness. We show that unsupervisedly trained point cloud models can outperform their supervised counterparts on downstream classification tasks. Most notably, by simply increasing the channel width of an SSG PointNet++, our unsupervised model surpasses the state-of-the-art supervised methods on both synthetic and real-world 3D object classification datasets. We expect our observations to offer a new perspective on learning better representation from data structures instead of human annotations for point cloud understanding.
In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task. The model exploits multi-label prediction to reveal the object category information in each image and then uses the prediction results to perform conditional adversarial global feature alignment, such that the multi-modal structure of image features can be tackled to bridge the domain divergence at the global feature level while preserving the discriminability of the features. Moreover, we introduce a prediction consistency regularization mechanism to assist object detection, which uses the multi-label prediction results as an auxiliary regularization information to ensure consistent object category discoveries between the object recognition task and the object detection task. Experiments are conducted on a few benchmark datasets and the results show the proposed model outperforms the state-of-the-art comparison methods.
Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions, such as the availability of all views in training and inference time. In this work, the problem of multiview self-supervised learning (MV-SSL) is investigated, where only image to object association is given. Given this setup, a novel surrogate task for self-supervised learning is proposed by pursuing "object invariant" representation. This is solved by randomly selecting an image feature of an object as object prototype, accompanied with multiview consistency regularization, which results in view invariant stochastic prototype embedding (VISPE). Experiments shows that the recognition and retrieval results using VISPE outperform that of other self-supervised learning methods on seen and unseen data. VISPE can also be applied to semi-supervised scenario and demonstrates robust performance with limited data available. Code is available at https://github.com/chihhuiho/VISPE
X-ray Computed Tomography (CT) based 3D imaging is widely used in airports for aviation security screening whilst prior work on prohibited item detection focuses primarily on 2D X-ray imagery. In this paper, we aim to evaluate the possibility of extending the automatic prohibited item detection from 2D X-ray imagery to volumetric 3D CT baggage security screening imagery. To these ends, we take advantage of 3D Convolutional Neural Neworks (CNN) and popular object detection frameworks such as RetinaNet and Faster R-CNN in our work. As the first attempt to use 3D CNN for volumetric 3D CT baggage security screening, we first evaluate different CNN architectures on the classification of isolated prohibited item volumes and compare against traditional methods which use hand-crafted features. Subsequently, we evaluate object detection performance of different architectures on volumetric 3D CT baggage images. The results of our experiments on Bottle and Handgun datasets demonstrate that 3D CNN models can achieve comparable performance (98% true positive rate and 1.5% false positive rate) to traditional methods but require significantly less time for inference (0.014s per volume). Furthermore, the extended 3D object detection models achieve promising performance in detecting prohibited items within volumetric 3D CT baggage imagery with 76% mAP for bottles and 88% mAP for handguns, which shows both the challenge and promise of such threat detection within 3D CT X-ray security imagery.
We present a novel approach to reconstructing lightweight, CAD-based representations of scanned 3D environments from commodity RGB-D sensors. Our key idea is to jointly optimize for both CAD model alignments as well as layout estimations of the scanned scene, explicitly modeling inter-relationships between objects-to-objects and objects-to-layout. Since object arrangement and scene layout are intrinsically coupled, we show that treating the problem jointly significantly helps to produce globally-consistent representations of a scene. Object CAD models are aligned to the scene by establishing dense correspondences between geometry, and we introduce a hierarchical layout prediction approach to estimate layout planes from corners and edges of the scene.To this end, we propose a message-passing graph neural network to model the inter-relationships between objects and layout, guiding generation of a globally object alignment in a scene. By considering the global scene layout, we achieve significantly improved CAD alignments compared to state-of-the-art methods, improving from 41.83% to 58.41% alignment accuracy on SUNCG and from 50.05% to 61.24% on ScanNet, respectively. The resulting CAD-based representations makes our method well-suited for applications in content creation such as augmented- or virtual reality.
Interactive video object segmentation (iVOS) aims at efficiently harvesting high-quality segmentation masks of the target object in a video with user interactions. Most previous state-of-the-arts tackle the iVOS with two independent networks for conducting user interaction and temporal propagation, respectively, leading to inefficiencies during the inference stage. In this work, we propose a unified framework, named Memory Aggregation Networks (MA-Net), to address the challenging iVOS in a more efficient way. Our MA-Net integrates the interaction and the propagation operations into a single network, which significantly promotes the efficiency of iVOS in the scheme of multi-round interactions. More importantly, we propose a simple yet effective memory aggregation mechanism to record the informative knowledge from the previous interaction rounds, improving the robustness in discovering challenging objects of interest greatly. We conduct extensive experiments on the validation set of DAVIS Challenge 2018 benchmark. In particular, our MA-Net achieves the J@60 score of 76.1% without any bells and whistles, outperforming the state-of-the-arts with more than 2.7%.
In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking framework. Since our tracker can work with detections coming either from unsupervised and supervised object detectors, we also investigated the impact of supervised and unsupervised detection inputs in our method and for tracking road users in general. We also compared our results with existing methods that were applied on the UA-Detrac and the UrbanTracker datasets. Results show that our proposed method is performing very well in both datasets with different inputs (MOTA ranging from 0:3491 to 0:5805 for unsupervised inputs on the UrbanTracker dataset and an average MOTA of 0:7638 for supervised inputs on the UA Detrac dataset) under different circumstances. A well-trained supervised object detector can give better results in challenging scenarios. However, in simpler scenarios, if good training data is not available, unsupervised method can perform well and can be a good alternative.
The detection of objects considering a 6DoF pose is a common requirement to build virtual and augmented reality applications. It is usually a complex task which requires real-time processing and high precision results for adequate user experience. Recently, different deep learning techniques have been proposed to detect objects in 6DoF in RGB images. However, they rely on high complexity networks, requiring a computational power that prevents them from working on mobile devices. In this paper, we propose an approach to reduce the complexity of 6DoF detection networks while maintaining accuracy. We used Knowledge Distillation to teach portables Convolutional Neural Networks (CNN) to learn from a real-time 6DoF detection CNN. The proposed method allows real-time applications using only RGB images while decreasing the hardware requirements. We used the LINEMOD dataset to evaluate the proposed method, and the experimental results show that the proposed method reduces the memory requirement by almost 99\% in comparison to the original architecture with the cost of reducing half the accuracy in one of the metrics. Code is available at https://github.com/heitorcfelix/singleshot6Dpose.
Implicit representations of 3D objects have recently achieved impressive results on learning-based 3D reconstruction tasks. While existing works use simple texture models to represent object appearance, photo-realistic image synthesis requires reasoning about the complex interplay of light, geometry and surface properties. In this work, we propose a novel implicit representation for capturing the visual appearance of an object in terms of its surface light field. In contrast to existing representations, our implicit model represents surface light fields in a continuous fashion and independent of the geometry. Moreover, we condition the surface light field with respect to the location and color of a small light source. Compared to traditional surface light field models, this allows us to manipulate the light source and relight the object using environment maps. We further demonstrate the capabilities of our model to predict the visual appearance of an unseen object from a single real RGB image and corresponding 3D shape information. As evidenced by our experiments, our model is able to infer rich visual appearance including shadows and specular reflections. Finally, we show that the proposed representation can be embedded into a variational auto-encoder for generating novel appearances that conform to the specified illumination conditions.
Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. These annotations are generally expensive to obtain and a common workaround is to generate and train on synthetic scenes, with the drawback of limited generalisation when the model is deployed in the real world. In this work, a two-stage 6D object pose estimator framework that can be applied on top of existing neural-network-based approaches and that does not require pose annotations on real images is proposed. The first self-supervised stage enforces the pose consistency between rendered predictions and real input images, narrowing the gap between the two domains. The second stage fine-tunes the previously trained model by enforcing the photometric consistency between pairs of different object views, where one image is warped and aligned to match the view of the other and thus enabling their comparison. In the absence of both real image annotations and depth information, applying the proposed framework on top of two recent approaches results in state-of-the-art performance when compared to methods trained only on synthetic data, domain adaptation baselines and a concurrent self-supervised approach on LINEMOD, LINEMOD OCCLUSION and HomebrewedDB datasets.
Object detection is an essential step towards holistic scene understanding. Most existing object detection algorithms attend to certain object areas once and then predict the object locations. However, neuroscientists have revealed that humans do not look at the scene in fixed steadiness. Instead, human eyes move around, locating informative parts to understand the object location. This active perceiving movement process is called \textit{saccade}. %In this paper, Inspired by such mechanism, we propose a fast and accurate object detector called \textit{SaccadeNet}. It contains four main modules, the \cenam, the \coram, the \atm, and the \aggatt, which allows it to attend to different informative object keypoints, and predict object locations from coarse to fine. The \coram~is used only during training to extract more informative corner features which brings free-lunch performance boost. On the MS COCO dataset, we achieve the performance of 40.4\% mAP at 28 FPS and 30.5\% mAP at 118 FPS. Among all the real-time object detectors, %that can run faster than 25 FPS, our SaccadeNet achieves the best detection performance, which demonstrates the effectiveness of the proposed detection mechanism.
Online and Real-time Object Tracking is an interesting workload that can be used to track objects (e.g., car, human, animal) in a series of video sequences in real-time. For simple object tracking on edge devices, the output of object tracking could be as simple as drawing a bounding box around a detected object and in some cases, the input matrices used in such computation are quite small (e.g., 4x7, 3x3, 5x5, etc). As a result, the amount of actual work is low. Therefore, a typical multi-threading based parallelization technique can not accelerate the tracking application; instead, a throughput based parallelization technique where each thread operates on independent video sequences is more rewarding. In this paper, we share our experience in parallelizing a Simple Online and Real-time Tracking (SORT) application on shared-memory multicores.
Neural Architecture Search (NAS) has achieved great success in image classification task. Some recent works have managed to explore the automatic design of efficient backbone or feature fusion layer for object detection. However, these methods focus on searching only one certain component of object detector while leaving others manually designed. We identify the inconsistency between searched component and manually designed ones would withhold the detector of stronger performance. To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures for all components (i.e. backbone, neck, and head) of object detector in an end-to-end manner. In addition, we empirically reveal that different parts of the detector prefer different operators. Motivated by this, we employ a novel scheme to automatically screen different sub search spaces for different components so as to perform the end-to-end search for each component on the corresponding sub search space efficiently. Without bells and whistles, our searched architecture, namely Hit-Detector, achieves 41.4\% mAP on COCO minival set with 27M parameters. Our implementation is available at https://github.com/ggjy/HitDet.pytorch.
We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout. This new setting allows users to provide the layout of salient objects only (i.e., foreground bounding boxes and categories), and lets the model complete the drawing with an invented background and a matching foreground. Two main challenges spring from this new task: (i) how to generate fine-grained details and realistic textures without segmentation map input; and (ii) how to create a background and weave it seamlessly into standalone objects. To tackle this, we propose Background Hallucination Generative Adversarial Network (BachGAN), which first selects a set of segmentation maps from a large candidate pool via a background retrieval module, then encodes these candidate layouts via a background fusion module to hallucinate a suitable background for the given objects. By generating the hallucinated background representation dynamically, our model can synthesize high-resolution images with both photo-realistic foreground and integral background. Experiments on Cityscapes and ADE20K datasets demonstrate the advantage of BachGAN over existing methods, measured on both visual fidelity of generated images and visual alignment between output images and input layouts.