Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for context modeling. We argue that scene understanding benefits from object relation reasoning, which is capable of mitigating the ambiguity of 3D object detections and thus helps locate and classify the 3D objects more accurately and robustly. To achieve this, we propose a novel 3D relation module (3DRM) which reasons about object relations at pair-wise levels. The 3DRM predicts the semantic and spatial relationships between objects and extracts the object-wise relation features. We demonstrate the effects of 3DRM by plugging it into proposal-based and voting-based 3D object detection pipelines, respectively. Extensive evaluations show the effectiveness and generalization of 3DRM on 3D object detection. Our source code is available at https://github.com/lanlan96/3DRM.
Object detection is a basic and important task in the field of aerial image processing and has gained much attention in computer vision. However, previous aerial image object detection approaches have insufficient use of scene semantic information between different regions of large-scale aerial images. In addition, complex background and scale changes make it difficult to improve detection accuracy. To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relat…
Peking University（北京大学）；SenseTime Group Limited（商汤科技集团有限公司）；Beijing University of Posts and Telecommunications（北京邮电大学）
Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. In order to avoid potential misleading contextual information aggregation in previous works, we propose a class-wise dynamic graph convolution (CDGC) module to adaptively propagate information. The graph reasoning is performed among pixels in the same class. Based on the proposed CDGC module, we further introduce the Class-wise Dynamic Graph Convolution Network(CDGCNet), which consists of two main…
Small object detection presents a significant challenge in computer vision and object detection. The performance of small object detectors is often compromised by a lack of pixels and less significant features. This issue stems from information misalignment caused by variations in feature scale and information loss during feature processing. In response to this challenge, this paper proposes a novel the Multi to Single Module (M2S), which enhances a specific layer through improving feature extraction and refining features. Specifically, M2S includes the proposed Cross-scale Aggregation Module …
Real-time semantic segmentation is playing a more important role in computer vision, due to the growing demand for mobile devices and autonomous driving. Therefore, it is very important to achieve a good trade-off among performance, model size and inference speed. In this paper, we propose a Channel-wise Feature Pyramid (CFP) module to balance those factors. Based on the CFP module, we built CFPNet for real-time semantic segmentation which applied a series of dilated convolution channels to extract effective features. Experiments on Cityscapes and CamVid datasets show that the proposed CFPNet …
As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance. Recently, due to the increasing demand for autonomous systems and robots, it is significant to make a tradeoff between accuracy and inference speed. In this paper, we propose a novel Depthwise Asymmetric Bottleneck (DAB) module to address this dilemma, which efficiently adopts depth-wise asymmetric convolution and dilated convolution to build a bottleneck structure. Based on the DAB module, we design a Depth-wise Asymmetric Bottleneck Network (DABNet) espe…
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works on refining 3D proposals have relied on human-designed components such as keypoints sampling, set abstraction and multi-scale feature fusion to produce powerful 3D object representations. Such methods, however, have limited ability to capture rich contextual dependencies among points. In this paper, we leverage the high-quality region proposal network and a…
Nanjing University Of Science And Technology（南京理工大学）
The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps (CAM) to generate pseudo masks as ground-truth. However, the existing methods typically depend on the painstaking training modules, which may bring in grinding computational overhead and complex training procedures. In this work, the semantic structure aware inference (SSA) is proposed to explore the semantic structure information hidden in different stages of the CNN-based network to generate high-quality CAM in the model inference. Specifically, the semantic structure modeling module (SSM) i…
Huazhong University of Science and Technology（华中科技大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches. We observe two crucial phenomena: 1) the detection accuracy of the hard objects, e.g., Pedestrians, is unsatisfactory, 2) when adding additional noise points, the performance of existing approaches decreases rapidly. To alleviate these problems, a novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module. By considering the channel-wise, point-wise and voxel-wise …
Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究院）
Convolutional neural networks typically perform poorly when the test (target domain) and training (source domain) data have significantly different distributions. While this problem can be mitigated by using the target domain data to align the source and target domain feature representations, the target domain data may be unavailable due to privacy concerns. Consequently, there is a need for methods that generalize well despite restricted access to target domain data during training. In this work, we propose an adversarial semantic hallucination approach (ASH), which combines a class-condition…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Depth information matters in RGB-D semantic segmentation task for providing additional geometric information to color images. Most existing methods exploit a multi-stage fusion strategy to propagate depth feature to the RGB branch. However, at the very deep stage, the propagation in a simple element-wise addition manner can not fully utilize the depth information. We propose Global-Local propagation network (GLPNet) to solve this problem. Specifically, a local context fusion module(L-CFM) is introduced to dynamically align both modalities before element-wise fusion, and a global context fusion…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Lingnan University（岭南大学）；Hong Kong Metropolitan University（香港都会大学）；The Education University of Hong Kong（香港教育大学）；Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics（南京航空航天大学深圳研究院）
Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing on informative areas to produce accurate 3D object detection results. This paper proposes a novel object detection network by semantical point-voxel feature interaction, dubbed PV-RCNN++. Unlike most of existing methods, PV-RCNN++ explores the semantic information to enhance the quality of object detection. First, a semantic segmentation module is proposed to retain more discriminative foreground keypoints. Such a mo…
Piece-wise 3D planar reconstruction provides holistic scene understanding of man-made environments, especially for indoor scenarios. Most recent approaches focused on improving the segmentation and reconstruction results by introducing advanced network architectures but overlooked the dual characteristics of piece-wise planes as objects and geometric models. Different from other existing approaches, we start from enforcing cross-task consistency for our multi-task convolutional neural network, PlaneRecNet, which integrates a single-stage instance segmentation network for piece-wise planar segm…
Recently, attention mechanisms have been explored with ConvNets, both across the spatial and channel dimensions. However, from our knowledge, all the existing methods devote the attention modules to capture local interactions from a uni-scale. In this paper, we propose a Previous Knowledge Channel Attention Module(PKCAM), that captures channel-wise relations across different layers to model the global context. Our proposed module PKCAM is easily integrated into any feed-forward CNN architectures and trained in an end-to-end fashion with a negligible footprint due to its lightweight property. W…
Autonomous driving is a challenging topic that requires complex solutions in perception tasks such as recognition of road, lanes, traffic signs or lights, vehicles and pedestrians. Through years of research, computer vision has grown capable of tackling these tasks with monocular detectors that can provide remarkable detection rates with relatively low processing times. However, the recent appearance of Convolutional Neural Networks (CNNs) has revolutionized the computer vision field and has made possible approaches to perform full pixel-wise semantic segmentation in times close to real time (…
Department of Electrical Engineering, City Univeristy of Hong Kong, Hong Kong
Noisy labels collected with limited annotation cost prevent medical image segmentation algorithms from learning precise semantic correlations. Previous segmentation arts of learning with noisy labels merely perform a pixel-wise manner to preserve semantics, such as pixel-wise label correction, but neglect the pair-wise manner. In fact, we observe that the pair-wise manner capturing affinity relations between pixels can greatly reduce the label noise rate. Motivated by this observation, we present a novel perspective for noisy mitigation by incorporating both pixel-wise and pair-wise manners, w…
We propose three segmentation methods using GAN and information leakage between generator and discriminator. First, we propose an Adversarial Training Attention Module (ATA-Module) that uses an attention mechanism from the discriminator to the generator to enhance and leak important information in the discriminator. ATA-Module transmits important information to the generator from the discriminator. Second, we propose a Top-Down Pixel-wise Difficulty Attention Module (Top-Down PDA-Module) that leaks an attention map based on pixel-wise difficulty in the generator to the discriminator. The gener…
We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder. Furthermore, to allow maximal adaptivity, the weights at each decoder block vary spatially. For this purpose, we design a new type of hypernetwork, composed of a nested U-Net for drawing higher level context features, a multi-headed weight generating module which generates the weights of each block in the decoder immediately before they are consumed, for efficient memory utilization, and a primary network that is composed of novel dynamic patch-w…
LMU München（慕尼黑大学）；Technische Universität München（慕尼黑工业大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Fully convolutional neural networks (F-CNNs) have set the state-of-the-art in image segmentation for a plethora of applications. Architectural innovations within F-CNNs have mainly focused on improving spatial encoding or network connectivity to aid gradient flow. In this paper, we explore an alternate direction of recalibrating the feature maps adaptively, to boost meaningful features, while suppressing weak ones. We draw inspiration from the recently proposed squeeze & excitation (SE) module for channel recalibration of feature maps for image classification. Towards this end, we introduce th…
Universidad de Zaragoza（萨拉戈萨大学）；Magic Leap（Magic Leap公司）；Bitbrain（Bitbrain公司）
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the curr…
YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detection
Chongqing University（重庆大学）；National University of Defense Technology（国防科技大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；China Academy of Information and Communications Technology（中国信息通信技术研究院）；Fawer Automotive Components Co., Ltd（法华汽车零部件有限公司）；Shenzhen University（深圳大学）；Inspur Yunzhou Industrial Internet Co., Ltd（Inspur Yunzhou 工业互联网有限公司）；Guoqi Zhimo (Chongqing) Technology Co., Ltd.（国基智（重庆）科技有限公司）
Department of Information Technology, Alpen-Adria-Universität Klagenfurt（克恩滕州阿尔卑斯-亚得里亚大学信息技术系）；Department of Ophthalmology, Klinikum Klagenfurt（克拉根福医院眼科）
Semantic segmentation in surgical videos is a prerequisite for a broad range of applications towards improving surgical outcomes and surgical video analysis. However, semantic segmentation in surgical videos involves many challenges. In particular, in cataract surgery, various features of the relevant objects such as blunt edges, color and context variation, reflection, transparency, and motion blur pose a challenge for semantic segmentation. In this paper, we propose a novel convolutional module termed as \textit{ReCal} module, which can calibrate the feature maps by employing region intra-an…
Northeastern University（东北大学）；Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University（东北大学医学影像智能计算教育部重点实验室）；Amii, University of Alberta（阿尔伯塔大学阿尔伯塔机器智能研究所）
Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UCTransNet (with a pro…
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we propose a differentiable forward rigid projection module that plays a key role in our instance-wise depth and motion learning. Second, we design an instance-wise photometric and geometric consistency loss that effectively decomposes background and moving object regions. Lastly, we introduce a new auto-annotation scheme to produce video instance segmentation m…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Institute of Technology（北京理工大学）；Horizon Robotics（地平线机器人）
Recently, multi-resolution networks (such as Hourglass, CPN, HRNet, etc.) have achieved significant performance on pose estimation by combining feature maps of various resolutions. In this paper, we propose a Resolution-wise Attention Module (RAM) and Gradual Pyramid Refinement (GPR), to learn enhanced resolution-wise feature maps for precise pose estimation. Specifically, RAM learns a group of weights to represent the different importance of feature maps across resolutions, and the GPR gradually merges every two feature maps from low to high resolutions to regress final human keypoint heatmap…
Learning Where to Focus: Density-Driven Guidance for Detecting Dense Tiny Objects
Key Laboratory of Intelligent Computing & Signal Processing (Anhui University), Ministry of Education（智能计算与信号处理重点实验室（安徽大学）、教育部）；Anhui Provincial Key Laboratory of Multimodal Cognitive Computation（安徽省多模态认知计算重点实验室）；School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；th Research Institute, China Electronics Technology Group Corporation（中国电子科技集团第三十八研究所）；Collaborative Innovation Laboratory for Computer Vision and Pattern Recognition, School of Artificial Intelligence and Big Data, Hefei University（计算机视觉与模式识别协同创新实验室，合肥大学人工智能与大数据学院）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）
6D pose estimation refers to object recognition and estimation of 3D rotation and 3D translation. The key technology for estimating 6D pose is to estimate pose by extracting enough features to find pose in any environment. Previous methods utilized depth information in the refinement process or were designed as a heterogeneous architecture for each data space to extract feature. However, these methods are limited in that they cannot extract sufficient feature. Therefore, this paper proposes a Point Attention Module that can efficiently extract powerful feature from RGB-D. In our Module, attent…
Northwestern Polytechnical University（西北工业大学）；Intel Labs（英特尔实验室）；The University of Sydney（悉尼大学）；University of Pittsburgh（匹兹堡大学）；JD Finance America Corporation（京东金融美国公司）
Automated and accurate segmentation of the infected regions in computed tomography (CT) images is critical for the prediction of the pathological stage and treatment response of COVID-19. Several deep convolutional neural networks (DCNNs) have been designed for this task, whose performance, however, tends to be suppressed by their limited local receptive fields and insufficient global reasoning ability. In this paper, we propose a pixel-wise sparse graph reasoning (PSGR) module and insert it into a segmentation network to enhance the modeling of long-range dependencies for COVID-19 infected re…
German Aerospace Center（德国航空航天中心）；Technical University of Munich（慕尼黑工业大学）
Multi-label classification plays a momentous role in perceiving intricate contents of an aerial image and triggers several related studies over the last years. However, most of them deploy few efforts in exploiting label relations, while such dependencies are crucial for making accurate predictions. Although an LSTM layer can be introduced to modeling such label dependencies in a chain propagation manner, the efficiency might be questioned when certain labels are improperly inferred. To address this, we propose a novel aerial image multi-label classification network, attention-aware label rela…
Pair-wise Layer Attention with Spatial Masking for Video Prediction
School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））；FABU Technology Co., Ltd.（法布科技有限公司）；College of Computer Science, Zhejiang University（浙江大学计算机学院）
Carnegie Mellon University（卡内基梅隆大学）；Xi’an Jiaotong University（西安交通大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Fudan University（复旦大学）；Kyoto University（京都大学）
Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID). Because of the indefinite number of targets among video frames, both subtasks are very difficult to scale up efficiently in end-to-end Deep Neural Networks (DNNs). In this paper, we design an end-to-end DNN tracking approach, Flow-Fuse-Tracker (FFT), that addresses the above issues with two efficient techniques: target flowing and target fusing. Specifically, in target flowing, a FlowTracker DNN module learns t…
Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；School of Software, Beihang University（北京航空航天大学软件学院）；School of Computing, National University of Singapore（新加坡国立大学计算学院）；Aviation Industry Development Research Center of China（中国航空工业发展研究中心）
Nanjing University of Science and Technology（南京理工大学）；University of Oxford（牛津大学）；University of Wollongong（伍伦贡大学）；The University of Adelaide（阿德莱德大学）
As a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the stan…
Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery
Beihang University（北京航空航天大学）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
In this work, we propose a novel neural network focusing on semantic labeling of ALS point clouds, which investigates the importance of long-range spatial and channel-wise relations and is termed as global relation-aware attentional network (GraNet). GraNet first learns local geometric description and local dependencies using a local spatial discrepancy attention convolution module (LoSDA). In LoSDA, the orientation information, spatial distribution, and elevation differences are fully considered by stacking several local spatial geometric learning modules and the local dependencies are embedd…
Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstrac…
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；City University of Hong Kong（香港城市大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；The Hong Kong University of Science and Technology（香港科技大学）；Nanyang Technological University（南洋理工大学）
Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
School of Computer Science and Technology, Guangdong University of Technology（广东工业大学计算机科学与技术学院）；Zhejiang Institute of Optoelectronics（浙江光电研究所）；School of Computer Science and Engineering, Huizhou University（惠州学院计算机科学与工程学院）；School of Information Science and Technology, Guangdong University of Foreign Studies（广东外语外贸大学信息科学与技术学院）；School of Physics, Maths and Computing, University of Western Australia（西澳大学物理、数学与计算学院）
Rotation invariance has been an important topic in computer vision tasks. Ideally, robot grasp detection should be rotation-invariant. However, rotation-invariance in robotic grasp detection has been only recently studied by using rotation anchor box that are often time-consuming and unreliable for multiple objects. In this paper, we propose a rotation ensemble module (REM) for robotic grasp detection using convolutions that rotates network weights. Our proposed REM was able to outperform current state-of-the-art methods by achieving up to 99.2% (image-wise), 98.6% (object-wise) accuracies on …
Shaanxi Normal University（陕西师范大学）；University of Georgia（佐治亚大学）；Northwestern Polytechnical University（西北工业大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）
Using deep learning models to recognize functional brain networks (FBNs) in functional magnetic resonance imaging (fMRI) has been attracting increasing interest recently. However, most existing work focuses on detecting static FBNs from entire fMRI signals, such as correlation-based functional connectivity. Sliding-window is a widely used strategy to capture the dynamics of FBNs, but it is still limited in representing intrinsic functional interactive dynamics at each time step. And the number of FBNs usually need to be set manually. More over, due to the complexity of dynamic interactions in …
Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images
School of Control Science and Engineering, Shandong University（控制科学与工程学院，山东大学）；Key Laboratory of Machine Intelligence and System Control, Ministry of Education（机器智能与系统控制重点实验室，教育部）；University of California, Los Angeles（加州大学洛杉矶分校）；Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences（智能地理信息处理重点实验室，中国地质大学）；Lingnan University（岭大大学）
