In the past few years, we have seen great progress in perception algorithms, particular through the use of deep learning. However, most existing approaches focus on a few categories of interest, which represent only a small fraction of the potential categories that robots need to handle in the real-world. Thus, identifying objects from unknown classes remains a challenging yet crucial task. In this paper, we develop a novel open-set instance segmentation algorithm for point clouds which can segment objects from both known and unknown classes in a holistic way. Our method uses a deep convolutional neural network to project points into a category-agnostic embedding space in which they can be clustered into instances irrespective of their semantics. Experiments on two large-scale self-driving datasets validate the effectiveness of our proposed method.
Object location is fundamental to panoptic segmentation as it is related to all things and stuff in the image scene. Knowing the locations of objects in the image provides clues for segmenting and helps the network better understand the scene. How to integrate object location in both thing and stuff segmentation is a crucial problem. In this paper, we propose spatial information flows to achieve this objective. The flows can bridge all sub-tasks in panoptic segmentation by delivering the object's spatial context from the box regression task to others. More importantly, we design four parallel sub-networks to get a preferable adaptation of object spatial information in sub-tasks. Upon the sub-networks and the flows, we present a location-aware and unified framework for panoptic segmentation, denoted as SpatialFlow. We perform a detailed ablation study on each component and conduct extensive experiments to prove the effectiveness of SpatialFlow. Furthermore, we achieve state-of-the-art results, which are $47.9$ PQ and $62.5$ PQ respectively on MS-COCO and Cityscapes panoptic benchmarks. Code will be available at https://github.com/chensnathan/SpatialFlow.
With the development of image segmentation in computer vision, biomedical image segmentation have achieved remarkable progress on brain tumor segmentation and Organ At Risk (OAR) segmentation. However, most of the research only uses single modality such as Computed Tomography (CT) scans while in real world scenario doctors often use multiple modalities to get more accurate result. To better leverage different modalities, we have collected a large dataset consists of 136 cases with CT and MR images which diagnosed with nasopharyngeal cancer. In this paper, we propose to use Generative Adversarial Network to perform CT to MR transformation to synthesize MR images instead of aligning two modalities. The synthesized MR can be jointly trained with CT to achieve better performance. In addition, we use instance segmentation model to extend the OAR segmentation task to segment both organs and tumor region. The collected dataset will be made public soon.
In the last few years, there has been a growing interest in taking advantage of the 360 panoramic images potential, while managing the new challenges they imply. While several tasks have been improved thanks to the contextual information these images offer, object recognition in indoor scenes still remains a challenging problem that has not been deeply investigated. This paper provides an object recognition system that performs object detection and semantic segmentation tasks by using a deep learning model adapted to match the nature of equirectangular images. From these results, instance segmentation masks are recovered, refined and transformed into 3D bounding boxes that are placed into the 3D model of the room. Quantitative and qualitative results support that our method outperforms the state of the art by a large margin and show a complete understanding of the main objects in indoor scenes.
We present Panoptic-DeepLab, a bottom-up and single-shot approach for panoptic segmentation. Our Panoptic-DeepLab is conceptually simple and delivers state-of-the-art results. In particular, we adopt the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. Our single Panoptic-DeepLab sets the new state-of-art at all three Cityscapes benchmarks, reaching 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set, and advances results on the other challenging Mapillary Vistas.
Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention modules for achieving better performance, which inevitably increase model complexity. To overcome the paradox of performance and complexity trade-off, this paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain. By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity. Therefore, we propose a local cross-channel interaction strategy without dimensionality reduction, which can be efficiently implemented via $1D$ convolution. Furthermore, we develop a method to adaptively select kernel size of $1D$ convolution, determining coverage of local cross-channel interaction. The proposed ECA module is efficient yet effective, e.g., the parameters and computations of our modules against backbone of ResNet50 are 80 vs. 24.37M and 4.7e-4 GFLOPs vs. 3.86 GFLOPs, respectively, and the performance boost is more than 2% in terms of Top-1 accuracy. We extensively evaluate our ECA module on image classification, object detection and instance segmentation with backbones of ResNets and MobileNetV2. The experimental results show our module is more efficient while performing favorably against its counterparts.
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progressively transform image-level labels to pixel-wise labels in a coarse-to-fine manner. We design four cascaded modules including multi-label classification, object detection, instance refinement and instance segmentation, which are implemented sequentially by sharing the same backbone. The cascaded pipeline is trained alternatively with a curriculum learning strategy that generalizes labels from high-level images to low-level pixels gradually with increasing accuracy. In addition, we design a proposal calibration module to explore the ability of classification networks to find key pixels that identify object parts, which serves as a post validation strategy running in the inverse order. We evaluate the efficiency of our Label-PEnet in mining instance masks on standard benchmarks: PASCAL VOC 2007 and 2012. Experimental results show that Label-PEnet outperforms the state-of-the-art algorithms by a clear margin, and obtains comparable performance even with the fully-supervised approaches.
Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data. In the context of autonomous vehicles perception, this requirement is critical, as the distribution of sensor data can continuously change and include several unexpected variations. It turns out that a category of learning techniques, referred to as self-supervised learning (SSL), consists of replacing the manual labeling effort by an automatic labeling process. Thanks to their ability to learn on the application time and in varying environments, state-of-the-art SSL techniques provide a valid alternative to supervised learning for a variety of different tasks, including long-range traversable area segmentation, moving obstacle instance segmentation, long-term moving obstacle tracking, or depth map prediction. In this tutorial-style article, we present an overview and a general formalization of the concept of self-supervised learning (SSL) for autonomous vehicles perception. This formalization provides helpful guidelines for developing novel frameworks based on generic SSL principles. Moreover, it enables to point out significant challenges in the design of future SSL systems.
In recent years, the task of segmenting foreground objects from background in a video, i.e. video object segmentation (VOS), has received considerable attention. In this paper, we propose a single end-to-end trainable deep neural network, convolutional gated recurrent Mask-RCNN, for tackling the semi-supervised VOS task. We take advantage of both the instance segmentation network (Mask-RCNN) and the visual memory module (Conv-GRU) to tackle the VOS task. The instance segmentation network predicts masks for instances, while the visual memory module learns to selectively propagate information for multiple instances simultaneously, which handles the appearance change, the variation of scale and pose and the occlusions between objects. After offline and online training under purely instance segmentation losses, our approach is able to achieve satisfactory results without any post-processing or synthetic video data augmentation. Experimental results on DAVIS 2016 dataset and DAVIS 2017 dataset have demonstrated the effectiveness of our method for video object segmentation task.
We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime. Our method trains a cohort of sub-networks with different widths using different input resolutions to mutually learn multi-scale representations for each sub-network. It achieves consistently better ImageNet top-1 accuracy over the state-of-the-art adaptive network US-Net under different computation constraints, and outperforms the best compound scaled MobileNet in EfficientNet by 1.5%. The superiority of our method is also validated on COCO object detection and instance segmentation as well as transfer learning. Surprisingly, the training strategy of MutualNet can also boost the performance of a single network, which substantially outperforms the powerful AutoAugmentation in both efficiency (GPU search hours: 15000 vs. 0) and accuracy (ImageNet: 77.6% vs. 78.6%). Code is available at \url{https://github.com/taoyang1122/MutualNet}.
We present a pipeline for geomorphological analysis that uses structure from motion (SfM) and deep learning on close-range aerial imagery to estimate spatial distributions of rock traits (size, roundness, and orientation) along a tectonic fault scarp. The properties of the rocks on the fault scarp derive from the combination of initial volcanic fracturing and subsequent tectonic and geomorphic fracturing, and our pipeline allows scientists to leverage UAS-based imagery to gain a better understanding of such surface processes. We start by using SfM on aerial imagery to produce georeferenced orthomosaics and digital elevation models (DEM). A human expert then annotates rocks on a set of image tiles sampled from the orthomosaics, and these annotations are used to train a deep neural network to detect and segment individual rocks in the entire site. The extracted semantic information (rock masks) on large volumes of unlabeled, high-resolution SfM products allows subsequent structural analysis and shape descriptors to estimate rock size, roundness, and orientation. We present results of two experiments conducted along a fault scarp in the Volcanic Tablelands near Bishop, California. We conducted the first, proof-of-concept experiment with a DJI Phantom 4 Pro equipped with an RGB camera and inspected if elevation information assisted instance segmentation from RGB channels. Rock-trait histograms along and across the fault scarp were obtained with the neural network inference. In the second experiment, we deployed a hexrotor and a multispectral camera to produce a DEM and five spectral orthomosaics in red, green, blue, red edge, and near infrared. We focused on examining the effectiveness of different combinations of input channels in instance segmentation.
The Active Contour Model (ACM) is a standard image analysis technique whose numerous variants have attracted an enormous amount of research attention across multiple fields. Incorrectly, however, the ACM's differential-equation-based formulation and prototypical dependence on user initialization have been regarded as being largely incompatible with the recently popular deep learning approaches to image segmentation. This paper introduces the first tight unification of these two paradigms. In particular, we devise Deep Convolutional Active Contours (DCAC), a truly end-to-end trainable image segmentation framework comprising a Convolutional Neural Network (CNN) and an ACM with learnable parameters. The ACM's Eulerian energy functional includes per-pixel parameter maps predicted by the backbone CNN, which also initializes the ACM. Importantly, both the CNN and ACM components are fully implemented in TensorFlow, and the entire DCAC architecture is end-to-end automatically differentiable and backpropagation trainable without user intervention. As a challenging test case, we tackle the problem of building instance segmentation in aerial images and evaluate DCAC on two publicly available datasets, Vaihingen and Bing Huts. Our reseults demonstrate that, for building segmentation, the DCAC establishes a new state-of-the-art performance by a wide margin.
The goal of salient region detection is to identify the regions of an image that attract the most attention. Many methods have achieved state-of-the-art performance levels on this task. Recently, salient instance segmentation has become an even more challenging task than traditional salient region detection; however, few of the existing methods have concentrated on this underexplored problem. Unlike the existing methods, which usually employ object proposals to roughly count and locate object instances, our method applies salient objects subitizing to predict an accurate number of instances for salient instance segmentation. In this paper, we propose a multitask densely connected neural network (MDNN) to segment salient instances in an image. In contrast to existing approaches, our framework is proposal-free and category-independent. The MDNN contains two parallel branches: the first is a densely connected subitizing network (DSN) used for subitizing prediction; the second is a densely connected fully convolutional network (DFCN) used for salient region detection. The MDNN simultaneously outputs saliency maps and salient object subitizing. Then, an adaptive deep feature-based spectral clustering operation segments the salient regions into instances based on the subitizing and saliency maps. The experimental results on both salient region detection and salient instance segmentation datasets demonstrate the satisfactory performance of our framework. Notably, its [email omitted] and [email omitted] reaches 73.46% and 60.14% in the salient instance dataset, substantially higher than the results achieved by the state-of-the-art algorithm.
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used as a mask prediction module for instance segmentation, by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on challenging COCO dataset. For the first time, we demonstrate a much simpler and flexible instance segmentation framework achieving competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation tasks. Code is available at: github.com/xieenze/PolarMask.
Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet (Multi-View PointNet), where we aggregate 2D multi-view image features into 3D point clouds, and then use a point based network to fuse the features in 3D canonical space to predict 3D semantic labels. To this end, we introduce view selection along with a 2D-3D feature aggregation module. Extensive experiments show the benefit of leveraging features from dense images and reveal superior robustness to varying point cloud density compared to 3D-only methods. On the ScanNetV2 benchmark, our MVPNet significantly outperforms prior point cloud based approaches on the task of 3D Semantic Segmentation. It is much faster to train than the large networks of the sparse voxel approach. We provide solid ablation studies to ease the future design of 2D-3D fusion methods and their extension to other tasks, as we showcase for 3D instance segmentation.
Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots. Certain existing studies have split input point clouds into small regions such as 1m x 1m; one reason for this is that models in the studies cannot consume a large number of points because of the large space complexity. However, because such small regions occasionally include a very small number of instances belonging to the same class, an evaluation using existing metrics such as mAP is largely affected by the category recognition performance. To address these problems, we propose a new method with space complexity O(Np) such that large regions can be consumed, as well as novel metrics for tasks that are independent of the categories or size of the inputs. Our method learns a mapping from input point clouds to an embedding space, where the embeddings form clusters for each instance and distinguish instances using these clusters during testing. Our method achieves state-of-the-art performance using both existing and the proposed metrics. Moreover, we show that our new metric can evaluate the performance of a task without being affected by any other condition.
In this work, we propose a generally applicable transformation unit for visual recognition with deep convolutional neural networks. This transformation explicitly models channel relationships with explainable control variables. These variables determine the neuron behaviors of competition or cooperation, and they are jointly optimized with the convolutional weight towards more accurate recognition. In Squeeze-and-Excitation (SE) Networks, the channel relationships are implicitly learned by fully connected layers, and the SE block is integrated at the block-level. We instead introduce a channel normalization layer to reduce the number of parameters and computational complexity. This lightweight layer incorporates a simple l2 normalization, enabling our transformation unit applicable to operator-level without much increase of additional parameters. Extensive experiments demonstrate the effectiveness of our unit with clear margins on many vision tasks, i.e., image classification on ImageNet, object detection and instance segmentation on COCO, video classification on Kinetics.
In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes these "rescans" to infer a temporal model of a scene with semantic instance information. Our algorithm operates inductively by using the temporal model resulting from past observations to infer an instance segmentation of a new scan, which is then used to update the temporal model. The model contains object instance associations across time and thus can be used to track individual objects, even though there are only sparse observations. During experiments with a new benchmark for the new task, our algorithm outperforms alternate approaches based on state-of-the-art networks for semantic instance segmentation.
We present Adaptive Instance Selection network architecture for class-agnostic instance segmentation. Given an input image and a point $(x, y)$, it generates a mask for the object located at $(x, y)$. The network adapts to the input point with a help of AdaIN layers, thus producing different masks for different objects on the same image. AdaptIS generates pixel-accurate object masks, therefore it accurately segments objects of complex shape or severely occluded ones. AdaptIS can be easily combined with standard semantic segmentation pipeline to perform panoptic segmentation. To illustrate the idea, we perform experiments on a challenging toy problem with difficult occlusions. Then we extensively evaluate the method on panoptic segmentation benchmarks. We obtain state-of-the-art results on Cityscapes and Mapillary even without pretraining on COCO, and show competitive results on a challenging COCO dataset. The source code of the method and the trained models are available at https://github.com/saic-vul/adaptis.
Deep neural networks show high accuracy in theproblem of semantic and instance segmentation of biomedicaldata. However, this approach is computationally expensive. Thecomputational cost may be reduced with network simplificationafter training or choosing the proper architecture, which providessegmentation with less accuracy but does it much faster. In thepresent study, we analyzed the accuracy and performance ofUNet and ENet architectures for the problem of semantic imagesegmentation. In addition, we investigated the ENet architecture by replacing of some convolution layers with box-convolutionlayers. The analysis performed on the original dataset consisted of histology slices with mast cells. These cells provide a region forsegmentation with different types of borders, which vary fromclearly visible to ragged. ENet was less accurate than UNet byonly about 1-2%, but ENet performance was 8-15 times faster than UNet one.