We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image for autonomous driving. Our approach combines the strengths of deep learning and the elegance of traditional techniques from part-based deformable model representation to produce high-quality 3D models in the presence of severe occlusions. We present a new part-based deformable vehicle model that is used for instance segmentation and automatically generate a dataset that contains dense correspondences between 2D images and 3D models. We also present a novel end-to-end deep neural network to predict dense 2D/3D mapping and highlight its benefits. Based on the dense mapping, we are able to compute precise 6-DoF poses and 3D reconstruction results at almost interactive rates on a commodity GPU. We have integrated these algorithms with an autonomous driving system. In practice, our method outperforms the state-of-the-art methods for all major vehicle parsing tasks: 2D instance segmentation by 4.4 points (mAP), 6-DoF pose estimation by 9.11 points, and 3D detection by 1.37. Moreover, we have released all of the source code, dataset, and the trained model on Github.
This paper presents TrashCan, a large dataset comprised of images of underwater trash collected from a variety of sources, annotated both using bounding boxes and segmentation labels, for development of robust detectors of marine debris. The dataset has two versions, TrashCan-Material and TrashCan-Instance, corresponding to different object class configurations. The eventual goal is to develop efficient and accurate trash detection methods suitable for onboard robot deployment. Along with information about the construction and sourcing of the TrashCan dataset, we present initial results of instance segmentation from Mask R-CNN and object detection from Faster R-CNN. These do not represent the best possible detection results but provides an initial baseline for future work in instance segmentation and object detection on the TrashCan dataset.
In order to function in unstructured environments, robots need the ability to recognize unseen objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However, the type of large-scale real-world dataset required for this task typically does not exist for most robotic settings, which motivates the use of synthetic data. Our proposed method, UOIS-Net, separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. UOIS-Net is comprised of two stages: first, it operates only on depth to produce object instance center votes in 2D or 3D and assembles them into rough initial masks. Secondly, these initial masks are refined using RGB. Surprisingly, our framework is able to learn from synthetic RGB-D data where the RGB is non-photorealistic. To train our method, we introduce a large-scale synthetic dataset of random objects on tabletops. We show that our method can produce sharp and accurate segmentation masks, outperforming state-of-the-art methods on unseen object instance segmentation. We also show that our method can segment unseen objects for robot grasping.
Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement. We introduce verification tasks into the localization prediction of RepPoints, producing RepPoints v2, which provides consistent improvements of about 2.0 mAP over the original RepPoints on the COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on COCO \texttt{test-dev} by a single model. Moreover, we show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation. The code is available at https://github.com/Scalsol/RepPointsV2.
A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects. We conduct detailed experiments on two datasets, going beyond the visual complexity supported by state-of-the-art generative approaches. We evaluate our method on depth-prediction and 3D object detection -- tasks which cannot be addressed by those earlier works -- and show it out-performs them even on 2D instance segmentation and tracking.
As a proposal-free approach, instance segmentation through pixel embedding learning and clustering is gaining more emphasis. Compared with bounding box refinement approaches, such as Mask R-CNN, it has potential advantages in handling complex shapes and dense objects. In this work, we propose a simple, yet highly effective, architecture for object-aware embedding learning. A distance regression module is incorporated into our architecture to generate seeds for fast clustering. At the same time, we show that the features learned by the distance regression module are able to promote the accuracy of learned object-aware embeddings significantly. By simply concatenating features of the distance regression module to the images as inputs of the embedding module, the mSBD scores on the CVPPP Leaf Segmentation Challenge can be further improved by more than 8% compared to the identical set-up without concatenation, yielding the best overall result amongst the leaderboard at CodaLab.
Assigning consistent temporal identifiers to multiple moving objects in a video sequence is a challenging problem. A solution to that problem would have immediate ramifications in multiple object tracking and segmentation problems. We propose a strategy that treats the temporal identification task as a spatio-temporal clustering problem. We propose an unsupervised learning approach using a convolutional and fully connected autoencoder, which we call deep heterogeneous autoencoder, to learn discriminative features from segmentation masks and detection bounding boxes. We extract masks and their corresponding bounding boxes from a pretrained instance segmentation network and train the autoencoders jointly using task-dependent uncertainty weights to generate common latent features. We then construct constraints graphs that encourage associations among objects that satisfy a set of known temporal conditions. The feature vectors and the constraints graphs are then provided to the kmeans clustering algorithm to separate the corresponding data points in the latent space. We evaluate the performance of our method using challenging synthetic and real-world multiple-object video datasets. Our results show that our technique outperforms several state-of-the-art methods.
We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning. The raw 3D reconstruction of an indoor environment suffers from occlusions, noise, and is produced without any meaningful distinction between individual entities. For high-level intelligent tasks from a large scale scene, 3D instance segmentation recognizes individual instances of objects. We approach the instance segmentation by simply learning the correct embedding space that maps individual instances of objects into distinct clusters that reflect both spatial and semantic information. Unlike previous approaches that require complex pre-processing or post-processing, our implementation is compact and fast with competitive performance, maintaining scalability on large scenes with high resolution voxels. We demonstrate the state-of-the-art performance of our algorithm in the ScanNet 3D instance segmentation benchmark on AP score.
Liquid Argon Time Projection Chambers (LArTPCs) are high resolution particle imaging detectors, employed by accelerator-based neutrino oscillation experiments for high precision physics measurements. While images of particle trajectories are intuitive to analyze for physicists, the development of a high quality, automated data reconstruction chain remains challenging. One of the most critical reconstruction steps is particle clustering: the task of grouping 3D image pixels into different particle instances that share the same particle type. In this paper, we propose the first scalable deep learning algorithm for particle clustering in LArTPC data using sparse convolutional neural networks (SCNN). Building on previous works on SCNNs and proposal free instance segmentation, we build an end-to-end trainable instance segmentation network that learns an embedding of the image pixels to perform point cloud clustering in a transformed space. We benchmark the performance of our algorithm on PILArNet, a public 3D particle imaging dataset, with respect to common clustering evaluation metrics. 3D pixels were successfully clustered into individual particle trajectories with 90% of them having an adjusted Rand index score greater than 92% with a mean pixel clustering efficiency and purity above 96%. This work contributes to the development of an end-to-end optimizable full data reconstruction chain for LArTPCs, in particular pixel-based 3D imaging detectors including the near detector of the Deep Underground Neutrino Experiment. Our algorithm is made available in the open access repository, and we share our Singularity software container, which can be used to reproduce our work on the dataset.
Automatic instance segmentation of glomeruli within kidney Whole Slide Imaging (WSI) is essential for clinical research in renal pathology. In computer vision, the end-to-end instance segmentation methods (e.g., Mask-RCNN) have shown their advantages relative to detect-then-segment approaches by performing complementary detection and segmentation tasks simultaneously. As a result, the end-to-end Mask-RCNN approach has been the de facto standard method in recent glomerular segmentation studies, where downsampling and patch-based techniques are used to properly evaluate the high resolution images from WSI (e.g., >10,000x10,000 pixels on 40x). However, in high resolution WSI, a single glomerulus itself can be more than 1,000x1,000 pixels in original resolution which yields significant information loss when the corresponding features maps are downsampled via the Mask-RCNN pipeline. In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework. Beyond such a comparison, we also comprehensively evaluate the performance of our detect-then-segment pipeline through: 1) two of the most prevalent segmentation backbones (U-Net and DeepLab_v3); 2) six different image resolutions (from 512x512 to 28x28); and 3) two different color spaces (RGB and LAB). Our detect-then-segment pipeline, with the DeepLab_v3 segmentation framework operating on previously detected glomeruli of 512x512 resolution, achieved a 0.953 dice similarity coefficient (DSC), compared with a 0.902 DSC from the end-to-end Mask-RCNN pipeline. Further, we found that neither RGB nor LAB color spaces yield better performance when compared against each other in the context of a detect-then-segment framework. Detect-then-segment pipeline achieved better segmentation performance compared with End-to-end method.
A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the image features extracted at a central point contain limited information for predicting distant keypoints or bounding box boundaries, due to object deformation and scale/orientation variation. To facilitate inference, we propose to instead perform regression from a set of points placed at more advantageous positions. This point set is arranged to reflect a good initialization for the given task, such as modes in the training data for pose estimation, which lie closer to the ground truth than the central point and provide more informative features for regression. As the utility of a point set depends on how well its scale, aspect ratio and rotation matches the target, we adopt the anchor box technique of sampling these transformations to generate additional point-set candidates. We apply this proposed framework, called Point-Set Anchors, to object detection, instance segmentation, and human pose estimation. Our results show that this general-purpose approach can achieve performance competitive with state-of-the-art methods for each of these tasks. Code is available at \url{https://github.com/FangyunWei/PointSetAnchor}
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework. To begin with, PointTrack adopts an efficient one-stage framework for instance segmentation, and learns instance embeddings by converting compact image representations to un-ordered 2D point cloud. Compared with PointTrack, our proposed PointTrack++ offers three major improvements. Firstly, in the instance segmentation stage, we adopt a semantic segmentation decoder trained with focal loss to improve the instance selection quality. Secondly, to further boost the segmentation performance, we propose a data augmentation strategy by copy-and-paste instances into training images. Finally, we introduce a better training strategy in the instance association stage to improve the distinguishability of learned instance embeddings. The resulting framework achieves the state-of-the-art performance on the 5th BMTT MOTChallenge.
Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which looks like a piecewise linear function of the network stage. In this paper, we study an effective channel dimension configuration towards better performance than the convention. To this end, we empirically study how to design a single layer properly by analyzing the rank of the output feature. We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction. Based on the investigation, we propose a simple yet effective channel configuration that can be parameterized by the layer index. As a result, our proposed model following the channel parameterization achieves remarkable performance on ImageNet classification and transfer learning tasks including COCO object detection, COCO instance segmentation, and fine-grained classifications. Code and ImageNet pretrained models are available at https://github.com/clovaai/rexnet.
Object detection or localization is an incremental step in progression from coarse to fine digital image inference. It not only provides the classes of the image objects, but also provides the location of the image objects which have been classified. The location is given in the form of bounding boxes or centroids. Semantic segmentation gives fine inference by predicting labels for every pixel in the input image. Each pixel is labelled according to the object class within which it is enclosed. Furthering this evolution, instance segmentation gives different labels for separate instances of objects belonging to the same class. Hence, instance segmentation may be defined as the technique of simultaneously solving the problem of object detection as well as that of semantic segmentation. In this survey paper on instance segmentation -- its background, issues, techniques, evolution, popular datasets, related work up to the state of the art and future scope have been discussed. The paper provides valuable information for those who want to do research in the field of instance segmentation.
In this paper, we study the problem of efficiently assessing building damage after natural disasters like hurricanes, floods or fires, through aerial video analysis. We make two main contributions. The first contribution is a new dataset, consisting of user-generated aerial videos from social media with annotations of instance-level building damage masks. This provides the first benchmark for quantitative evaluation of models to assess building damage using aerial videos. The second contribution is a new model, namely MSNet, which contains novel region proposal network designs and an unsupervised score refinement network for confidence score calibration in both bounding box and mask branches. We show that our model achieves state-of-the-art results compared to previous methods in our dataset. We will release our data, models and code.
We present a work-flow which aims at capturing residents' abnormal activities through the passenger flow of elevator in multi-storey residence buildings. Camera and sensors (hall sensor, photoelectric sensor, gyro, accelerometer, barometer, and thermometer) with internet connection are mounted in elevator to collect image and data. Computer vision algorithms such as instance segmentation, multi-label recognition, embedding and clustering are applied to generalize passenger flow of elevator, i.e. how many people and what kinds of people get in and out of the elevator on each floor. More specifically in our implementation we propose GraftNet, a solution for fine-grained multi-label recognition task, to recognize human attributes, e.g. gender, age, appearance, and occupation. Then anomaly detection of unsupervised learning is hierarchically applied on the passenger flow data to capture abnormal or even illegal activities of the residents which probably bring safety hazard, e.g. drug dealing, pyramid sale gathering, prostitution, and over crowded residence. Experiment shows effects are there, and the captured records will be directly reported to our customer(property managers) for further confirmation.
We propose a novel 3D point cloud segmentation framework named SASO, which jointly performs semantic and instance segmentation tasks. For semantic segmentation task, inspired by the inherent correlation among objects in spatial context, we propose a Multi-scale Semantic Association (MSA) module to explore the constructive effects of the semantic context information. For instance segmentation task, different from previous works that utilize clustering only in inference procedure, we propose a Salient Point Clustering Optimization (SPCO) module to introduce a clustering procedure into the training process and impel the network focusing on points that are difficult to be distinguished. In addition, because of the inherent structures of indoor scenes, the imbalance problem of the category distribution is rarely considered but severely limits the performance of 3D scene perception. To address this issue, we introduce an adaptive Water Filling Sampling (WFS) algorithm to balance the category distribution of training data. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods on benchmark datasets in both semantic segmentation and instance segmentation tasks.
Deep learning-based methods are gaining traction in digital pathology, with an increasing number of publications and challenges that aim at easing the work of systematically and exhaustively analyzing tissue slides. These methods often achieve very high accuracies, at the cost of requiring large annotated datasets to train. This requirement is especially difficult to fulfill in the medical field, where expert knowledge is essential. In this paper we focus on nuclei segmentation, which generally requires experienced pathologists to annotate the nuclear areas in gigapixel histological images. We propose an algorithm for instance segmentation that uses pseudo-label segmentations generated automatically from point annotations, as a method to reduce the burden for pathologists. With the generated segmentation masks, the proposed method trains a modified version of HoVer-Net model to achieve instance segmentation. Experimental results show that the proposed method is robust to inaccuracies in point annotations and comparison with Hover-Net trained with fully annotated instance masks shows that a degradation in segmentation performance does not always imply a degradation in higher order tasks such as tissue classification.
Panoptic segmentation has become a new standard of visual recognition task by unifying previous semantic segmentation and instance segmentation tasks in concert. In this paper, we propose and explore a new video extension of this task, called video panoptic segmentation. The task requires generating consistent panoptic segmentation as well as an association of instance ids across video frames. To invigorate research on this new task, we present two types of video panoptic datasets. The first is a re-organization of the synthetic VIPER dataset into the video panoptic format to exploit its large-scale pixel annotations. The second is a temporal extension on the Cityscapes val. set, by providing new video panoptic annotations (Cityscapes-VPS). Moreover, we propose a novel video panoptic segmentation network (VPSNet) which jointly predicts object classes, bounding boxes, masks, instance id tracking, and semantic segmentation in video frames. To provide appropriate metrics for this task, we propose a video panoptic quality (VPQ) metric and evaluate our method and several other baselines. Experimental results demonstrate the effectiveness of the presented two datasets. We achieve state-of-the-art results in image PQ on Cityscapes and also in VPQ on Cityscapes-VPS and VIPER datasets. The datasets and code are made publicly available.
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We find existing detection methods are unable to model few-shot classes when the dataset is extremely skewed, which can result in classifier imbalance in terms of parameter magnitude. Directly adapting long-tail classification models to detection frameworks can not solve this problem due to the intrinsic difference between detection and classification.In this work, we propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training. It implicitly modulates the training process for the head and tail classes and ensures they are both sufficiently trained, without requiring any extra sampling for the instances from the tail classes.Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors with various backbones and frameworks on both object detection and instance segmentation. It beats all state-of-the-art methods transferred from long-tail image classification and establishes new state-of-the-art.Code is available at https://github.com/FishYuLi/BalancedGroupSoftmax.