To satisfy the stringent requirements on computational resources in the field of real-time semantic segmentation, most approaches focus on the hand-crafted design of light-weight segmentation networks. Recently, Neural Architecture Search (NAS) has been used to search for the optimal building blocks of networks automatically, but the network depth, downsampling strategy, and feature aggregation way are still set in advance by trial and error. In this paper, we propose a joint search framework, called AutoRTNet, to automate the design of these strategies. Specifically, we propose hyper-cells to jointly decide the network depth and downsampling strategy, and an aggregation cell to achieve automatic multi-scale feature aggregation. Experimental results show that AutoRTNet achieves 73.9% mIoU on the Cityscapes test set and 110.0 FPS on an NVIDIA TitanXP GPU card with 768x1536 input images.
Facebook Inc.（脸书公司）；University of Waterloo（滑铁卢大学）；TAL Education（好未来教育）
Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component. To speed up performance, it is common to downsample the input frame. However, this comes at the cost of missed small objects and reduced accuracy at semantic boundaries. To address this problem, we propose a new content-adaptive downsampling technique that learns to favor sampling locations near semantic boundaries of target classes. Cost-performance analysis shows that our method consistently outperforms the uniform sampling improving balance between accuracy and computational efficien…
Successful visual recognition networks benefit from aggregating information spanning from a wide range of scales. Previous research has investigated information fusion of connected layers or multiple branches in a block, seeking to strengthen the power of multi-scale representations. Despite their great successes, existing practices often allocate the neurons for each scale manually, and keep the same ratio in all aggregation blocks of an entire network, rendering suboptimal performance. In this paper, we propose to learn the neuron allocation for aggregating multi-scale information in differe…
In this paper, we propose an end to end solution for image matting i.e high-precision extraction of foreground objects from natural images. Image matting and background detection can be achieved easily through chroma keying in a studio setting when the background is either pure green or blue. Nonetheless, image matting in natural scenes with complex and uneven depth backgrounds remains a tedious task that requires human intervention. To achieve complete automatic foreground extraction in natural scenes, we propose a method that assimilates semantic segmentation and deep image matting processes…
Huazhong University of Science and Technology（华中科技大学）；The University of Adelaide（阿德莱德大学）；The Chinese University of Hong Kong（香港中文大学）；Tencent（腾讯）
The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable accuracy decrease. We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation. To this end, we propose an efficient and effective architecture with a good trade-off between speed and accuracy, termed Bilateral Segmentation Network (BiSeNet V2). This architectur…
Northeastern University（东北大学）；Shengjing Hospital, China Medical University（中国医科大学附属盛京医院）
In this paper, we propose a dual aggregation network to adaptively aggregate different information in infant brain MRI segmentation. More precisely, we added two modules based on 3D-UNet to better model information at different levels and locations. The dilated convolution pyramid downsampling module is mainly to solve the problem of loss of spatial information on the downsampling process, and it can effectively save details while reducing the resolution. The self-attention module can integrate the remote dependence on the feature maps in two dimensions of spatial and channel, effectively impr…
University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Research（商汤科技研究院）
Point clouds and RGB images are two general perceptional sources in autonomous driving. The former can provide accurate localization of objects, and the latter is denser and richer in semantic information. Recently, AutoAlign presents a learnable paradigm in combining these two modalities for 3D object detection. However, it suffers from high computational cost introduced by the global-wise attention. To solve the problem, we propose Cross-Domain DeformCAFA module in this work. It attends to sparse learnable sampling points for cross-modal relational modeling, which enhances the tolerance to c…
University of Science and Technology（科技大学）；Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；IIIS, Tsinghua University（清华大学智能产业研究院）
Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving. However, it remains challenging to make these two data sources complementary and beneficial to each other. In this paper, we propose \textit{AutoAlign}, an automatic feature fusion strategy for 3D object detection. Instead of establishing deterministic correspondence with camera projection matrix, we model the mapping relationship between the image and point clouds with a learnable alignment map. This map enables our model to automate the alignment of non-homogenous feature…
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；AAII, University of Technology Sydney（悉尼科技大学人工智能高级研究院）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；University of Oregon（俄勒冈大学）；Picsart AI Research（Picsart人工智能研究院）
Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation. However, most of the current popular network architectures tend to ignore the misalignment issues during the feature aggregation process caused by 1) step-by-step downsampling operations, and 2) indiscriminate contextual information fusion. In this paper, we explore the principles in addressing such feature misalignment issues and inventively propose Feature-Aligned Segmentation Networks (AlignSeg). Alig…
Semantic segmentation is an important task in computer vision, from which some important usage scenarios are derived, such as autonomous driving, scene parsing, etc. Due to the emphasis on the task of video semantic segmentation, we participated in this competition. In this report, we briefly introduce the solutions of team 'BetterThing' for the ICCV2021 - Video Scene Parsing in the Wild Challenge. Transformer is used as the backbone for extracting video frame features, and the final result is the aggregation of the output of two Transformer models, SWIN and VOLO. This solution achieves 57.3% …
Institution for Advanced Computer Studies（高级计算机研究所）；University of Maryland, College Park（马里兰大学帕克分校）
We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for capturing spatio-temporal information in videos. Since we do not apply 3D convolutions in each layer but only apply temporal aggregation blocks once after each spatial downsampling layer in the network, we significantly reduce the model complexity. The use of dilated convolutions at different resolutions of the network helps in aggregating multi-scale spatio-tempora…
We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network. The proposed RPN uses a novel architecture capable of performing multimodal feature fusion on high resolution feature maps to generate reliable 3D object proposals for multiple object classes in road scenes. Using these proposals, the second stage detection network performs accurate oriented 3D boun…
As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this issue, we propose a meta-learning framework with two novel feature aggregation schemes. More precisely, we first present a Class-Agnostic Aggregation (CAA) method, where the query and support features can be aggregated regardless of their categories. The interactions between different classes encourage class-agnostic representations and reduce confusion between b…
Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest. Nevertheless, on more difficult domains, such as dense per-pixel classification, current automatic approaches are limited in their scope - due to their strong reliance on existing image classifiers they tend to search only for a handful of additional layers with discovered architectures still containing a large number of parameters. In contrast, in this work we propose a novel solution able to find li…
3D morphable models are widely used for the shape representation of an object class in computer vision and graphics applications. In this work, we focus on deep 3D morphable models that directly apply deep learning on 3D mesh data with a hierarchical structure to capture information at multiple scales. While great efforts have been made to design the convolution operator, how to best aggregate vertex features across hierarchical levels deserves further attention. In contrast to resorting to mesh decimation, we propose an attention based module to learn mapping matrices for better feature aggre…
National University of Singapore（新加坡国立大学）；Massachusetts Institute of Technology（麻省理工学院）
The learning and aggregation of multi-scale features are essential in empowering neural networks to capture the fine-grained geometric details in the point cloud upsampling task. Most existing approaches extract multi-scale features from a point cloud of a fixed resolution, hence obtain only a limited level of details. Though an existing approach aggregates a feature hierarchy of different resolutions from a cascade of upsampling sub-network, the training is complex with expensive computation. To address these issues, we construct a new point cloud upsampling pipeline called BIMS-PU that integ…
Hunan University（湖南大学）；The University of Western Australia（西澳大学）
Point cloud processing methods exploit local point features and global context through aggregation which does not explicity model the internal correlations between local and global features. To address this problem, we propose full point encoding which is applicable to convolution and transformer architectures. Specifically, we propose Full Point Convolution (FPConv) and Full Point Transformer (FPTransformer) architectures. The key idea is to adaptively learn the weights from local and global geometric connections, where the connections are established through local and global correlation func…
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers lose the discriminative details due to improper pooling strategies, which could hinder the learning process and eventually result in suboptimal models. In this paper, we present a unified framework over the existing downsampling layers (e.g., average pooling, max pooling, and strided convolution) from a local importance view. In this framework, we analyze the…
University of Cambridge（剑桥大学）；HKUST(GuangZhou)（香港科技大学（广州））
Current point cloud segmentation architectures suffer from limited long-range feature modeling, as they mostly rely on aggregating information with local neighborhoods. Furthermore, in order to learn point features at multiple scales, most methods utilize a data-agnostic sampling approach to decrease the number of points after each stage. Such sampling methods, however, often discard points for small objects in the early stages, leading to inadequate feature learning. We believe these issues are can be mitigated by introducing explicit geometry clues as guidance. To this end, we propose GeoSpa…
University of Cambridge（剑桥大学）；University of Cincinnati（辛辛那提大学）
Quantitative cancer image analysis relies on the accurate delineation of tumours, a very specialised and time-consuming task. For this reason, methods for automated segmentation of tumours in medical imaging have been extensively developed in recent years, being Computed Tomography one of the most popular imaging modalities explored. However, the large amount of 3D voxels in a typical scan is prohibitive for the entire volume to be analysed at once in conventional hardware. To overcome this issue, the processes of downsampling and/or resampling are generally implemented when using traditional …
Accurate automatic organ segmentation is an important yet challenging problem for medical image analysis. The pancreas is an abdominal organ with very high anatomical variability. This inhibits traditional segmentation methods from achieving high accuracies, especially compared to other organs such as the liver, heart or kidneys. In this paper, we present a holistic learning approach that integrates semantic mid-level cues of deeply-learned organ interior and boundary maps via robust spatial aggregation using random forest. Our method generates boundary preserving pixel-wise class labels for p…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas A&M University（德克萨斯农工大学）；Horizon Robotics Inc（地平线机器人公司）
We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation. Recently, high-performance hand-crafted convolutional networks for pose estimation show growing demands on multi-scale fusion and high-resolution representations. However, current NAS works exhibit limited flexibility on scale searching, they dominantly adopt simplified search spaces of single-branch architectures. Such simplification limits the fusion of informati…
Guangzhou Institute of Technology, Xidian University（西安电子科技大学广州研究院）；Northwestern Polytechnical University（西北工业大学）
Existing methods for anomaly detection based on memory-augmented autoencoder (AE) have the following drawbacks: (1) Establishing a memory bank requires additional memory space. (2) The fixed number of prototypes from subjective assumptions ignores the data feature differences and diversity. To overcome these drawbacks, we introduce DLAN-AC, a Dynamic Local Aggregation Network with Adaptive Clusterer, for anomaly detection. First, The proposed DLAN can automatically learn and aggregate high-level features from the AE to obtain more representative prototypes, while freeing up extra memory space.…
Multi-instance learning is common for computer vision tasks, especially in biomedical image processing. Traditional methods for multi-instance learning focus on designing feature aggregation methods and multi-instance classifiers, where the aggregation operation is performed either in feature extraction or learning phase. As deep neural networks (DNNs) achieve great success in image processing via automatic feature learning, certain feature aggregation mechanisms need to be incorporated into common DNN architecture for multi-instance learning. Moreover, flexibility and reliability are crucial …
The University of Iceland（冰岛大学）；ETH Zürich（苏黎世联邦理工学院）；The Icelandic Heart Association（冰岛心脏协会）；The Johns Hopkins University（约翰斯·霍普金斯大学）
Osteoporosis is a common bone disease that occurs when the creation of new bone does not keep up with the loss of old bone, resulting in increased fracture risk. Adults over the age of 50 are especially at risk and see their quality of life diminished because of limited mobility, which can lead to isolation and depression. We are developing a robust screening method capable of identifying individuals predisposed to hip fracture to address this clinical challenge. The method uses finite element analysis and relies on segmented computed tomography (CT) images of the hip. Presently, the segmentat…
McGill University（麦吉尔大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人学会）
Natural image matting aims to precisely separate foreground objects from background using alpha matte. Fully automatic natural image matting without external annotation is challenging. Well-performed matting methods usually require accurate labor-intensive handcrafted trimap as extra input, while the performance of automatic trimap generation method of dilating foreground segmentation fluctuates with segmentation quality. Therefore, we argue that how to handle trade-off of additional information input is a major issue in automatic matting. This paper presents a semantic-guided automatic natura…
The Chinese University of Hong Kong（香港中文大学）；Imsight Medical Technology, Co., Ltd.（Imsight医疗科技有限公司）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Automatic detection of cancer metastasis from whole slide images (WSIs) is a crucial step for following patient staging and prognosis. Recent convolutional neural network based approaches are struggling with the trade-off between accuracy and computational efficiency due to the difficulty in processing large-scale gigapixel WSIs. To meet this challenge, we propose a novel Pyramidal Feature Aggregation ScanNet (PFA-ScanNet) for robust and fast analysis of breast cancer metastasis. Our method mainly benefits from the aggregation of extracted local-to-global features with diverse receptive fields…
National Institutes of Health Clinical Center（美国国立卫生研究院临床中心）
Accurate and automatic organ segmentation from 3D radiological scans is an important yet challenging problem for medical image analysis. Specifically, the pancreas demonstrates very high inter-patient anatomical variability in both its shape and volume. In this paper, we present an automated system using 3D computed tomography (CT) volumes via a two-stage cascaded approach: pancreas localization and segmentation. For the first step, we localize the pancreas from the entire 3D CT scan, providing a reliable bounding box for the more refined segmentation step. We introduce a fully deep-learning a…
Myocardial Region-guided Feature Aggregation Net for Automatic Coronary artery Segmentation and Stenosis Assessment using Coronary Computed Tomography Angiography
School of Computer Science and Technology, Zhengzhou University of Light Industry（郑州轻工业大学计算机与通信工程学院）；School of Information Management and Engineering, Shanghai University of Finance and Economics（上海财经大学信息管理与工程学院）；Department of Applied Computing, Michigan Technological University（密歇根理工大学应用计算系）；Health Research Institute, Michigan Technological University（密歇根理工大学健康研究所）；Department of Computer Science, Kennesaw State University（肯尼索州立大学计算机科学系）
BMW Group（宝马集团）；Technical University of Munich（慕尼黑工业大学）；Google Inc.（谷歌公司）
Driveable area detection is a key component for various applications in the field of autonomous driving (AD), such as ground-plane detection, obstacle detection and maneuver planning. Additionally, bulky and over-parameterized networks can be easily forgone and replaced with smaller networks for faster inference on embedded systems. The driveable area detection, posed as a two class segmentation task, can be efficiently modeled with slim binary networks. This paper proposes a novel binarized driveable area detection network (binary DAD-Net), which uses only binary weights and activations in th…
University of Technology Sydney（悉尼科技大学）；Griffith University（格里菲斯大学）
Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of adjacent image patches. So the challenge for this learning task is to simultaneously describe the geometric and semantic properties of objects or a scene. In this paper, we explore the effective use of multi-layer feature outputs of the deep parsing networks for spatial-semantic consistency by designing a novel feature aggregation module to generate the approp…
We propose a new approach to video face recognition. Our component-wise feature aggregation network (C-FAN) accepts a set of face images of a subject as an input, and outputs a single feature vector as the face representation of the set for the recognition task. The whole network is trained in two steps: (i) train a base CNN for still image face recognition; (ii) add an aggregation module to the base network to learn the quality value for each feature component, which adaptively aggregates deep feature vectors into a single vector to represent the face in a video. C-FAN automatically learns to…
Autonomous systems need to localize and track surrounding objects in 3D space for safe motion planning. As a result, 3D multi-object tracking (MOT) plays a vital role in autonomous navigation. Most MOT methods use a tracking-by-detection pipeline, which includes object detection and data association processing. However, many approaches detect objects in 2D RGB sequences for tracking, which is lack of reliability when localizing objects in 3D space. Furthermore, it is still challenging to learn discriminative features for temporally-consistent detection in different frames, and the affinity mat…
Towards Unifying Anatomy Segmentation: Automated Generation of a Full-body CT Dataset via Knowledge Aggregation and Anatomical Guidelines
Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院人机交互与机器人学研究所）；Institute for AI in Medicine, University Hospital Essen（埃森大学医院医学人工智能研究所）；Steinbuch Center for Computing, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院（KIT）施泰因布赫计算中心）；Department of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ）放射肿瘤学医学物理科）；Heidelberg Institute of Radiation Oncology (HIRO)（海德堡放射肿瘤学研究所（HIRO））；National Center for Radiation Research in Oncology (NCRO)（国家肿瘤放射研究中心（NCRO））；Helmholtz Information and Data Science School for Health (HIDSS4Health)（亥姆霍兹健康信息与数据科学学院（HIDSS4Health））；Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen（埃森大学医院诊断与介入放射学及神经放射学系）
Anticipation of accidents ahead of time in autonomous and non-autonomous vehicles aids in accident avoidance. In order to recognize abnormal events such as traffic accidents in a video sequence, it is important that the network takes into account interactions of objects in a given frame. We propose a novel Feature Aggregation (FA) block that refines each object's features by computing a weighted sum of the features of all objects in a frame. We use FA block along with Long Short Term Memory (LSTM) network to anticipate accidents in the video sequences. We report mean Average Precision (mAP) an…
Fueled by recent advances in machine learning, there has been tremendous progress in the field of semantic segmentation for the medical image computing community. However, developed algorithms are often optimized and validated by hand based on one task only. In combination with small datasets, interpreting the generalizability of the results is often difficult. The Medical Segmentation Decathlon challenge addresses this problem, and aims to facilitate development of generalizable 3D semantic segmentation algorithms that require no manual parametrization. Such an algorithm was developed and is …
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots. However, the rigid projection computed by ego-motion cannot represent all scene points, such as points on moving objects, leading to false guidance in these regions. To address this problem, we propose an Attentional Separation-and-Aggregation Network (ASANet), which can learn to distinguish and extract the scene's static and dynamic characteristics via the attention mechanism. We further propose …
Microsoft Research（微软研究院）；The Australian National University（澳大利亚国立大学）；Beijing Institute of Technology（北京理工大学）
This paper presents a Neural Aggregation Network (NAN) for video face recognition. The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which maps each face image to a feature vector. The aggregation module consists of two attention blocks which adaptively aggregate the feature vectors to form a single feature inside the convex hull spann…
New York University（纽约大学）；New York University Langone Medical Center（纽约大学朗格尼医学中心）
Early detection is a crucial goal in the study of Alzheimer's Disease (AD). In this work, we describe several techniques to boost the performance of 3D deep convolutional neural networks (CNNs) trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outperforms batch normalization, (2) early spatial downsampling negatively affects performance, (3) widening the model brings consistent gains while increasing the depth does not, and (4) incorporating age information yields moderate improvement. Together, these insights yield an incr…
Different from handcrafted features, deep neural networks can automatically learn task-specific features from data. Due to this data-driven nature, they have achieved remarkable success in various areas. However, manual design and selection of suitable network architectures are time-consuming and require substantial effort of human experts. To address this problem, researchers have proposed neural architecture search (NAS) algorithms which can automatically generate network architectures but suffer from heavy computational cost and instability if searching from scratch. In this paper, we propo…
