检索结果-内蒙古大学图书馆

HiT: Building Mapping with Hierarchical Transformers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Mingming Liu, Qingjie Wang, Yunhong The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Hangzhou Innovation Institute Beihang University Hangzhou310051 China

Deep learning-based methods have been extensively explored for automatic building mapping from high-resolution remote sensing images over recent years. While most building mapping models produce vector polygons of buildings for geographic and mapping systems, dominant methods typically decompose polygonal building extraction in some sub-problems, including segmentation, polygonization, and regularization, leading to complex inference procedures, low accuracy, and poor generalization. In this paper, we propose a simple and novel building mapping method with Hierarchical Transformers, called HiT, improving polygonal building mapping quality from high-resolution remote sensing images. HiT builds on a two-stage detection architecture by adding a polygon head parallel to classification and bounding box regression heads. HiT simultaneously outputs building bounding boxes and vector polygons, which is fully end-to-end trainable. The polygon head formulates a building polygon as serialized vertices with the bidirectional characteristic, a simple and elegant polygon representation avoiding the start or end vertex hypothesis. Under this new perspective, the polygon head adopts a transformer encoder-decoder architecture to predict serialized vertices supervised by the designed bidirectional polygon loss. Furthermore, a hierarchical attention mechanism combined with convolution operation is introduced in the encoder of the polygon head, providing more geometric structures of building polygons at vertex and edge levels. Comprehensive experiments on two benchmarks (the CrowdAI and Inria datasets) demonstrate that our method achieves a new state-of-the-art in terms of instance segmentation and polygonal metrics compared with state-of-the-art methods. Moreover, qualitative results verify the superiority and effectiveness of our model under complex scenes. Copyright © 2023, The Authors. All rights reserved.

关键词： Mapping

A Multi-Head Convolution Network with Attention Consistency for Facial Expression Recognition 42

学校读者我要写书评

暂无评论

A Multi-Head Convolution Network with Attention Consistency ...

42nd Chinese Control Conference, CCC 2023

作者： Liu, Wenkang Sun, Mingyi Li, Yang Beihang University The Department of Automation Science and Electrical Engineering Beijing100191 China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Peking University Advanced Institute of Information Technology Hangzhou310000 China

ISBN: (纸本)9789887581543

In recent years, the demand for facial expression recognition applications has increased rapidly, and its research has received extensive attention from researchers. However, the current recognition methods based on deep learning ignore the idea of multiple head attention and semantic consistency, resulting in the model only paying attention to the local area of the feature map. In addition, the model's inconsistent attention to the images before and after the flip, resulting the poor robustness, poor interpretation, and other shortcomings in the model. To address the above problems, we propose an Affinity Separation Loss (ASLoss), which improves the separability of samples through clustering. Moreover, a Separate Multi-head Attention block (SMA), and a Zonal Loss (ZLoss) are also designed to decentralize the model's attention. Experimental results demonstrate that our proposed MACNet method achieves competitive recognition performance on two public datasets RAF-DB and FERPlus. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Face recognition

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decoding Model for BCI Human-Machine Interaction 42

学校读者我要写书评

暂无评论

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decodi...

42nd Chinese Control Conference, CCC 2023

作者： Yan, Weidong Xu, Zhaoliang Li, Yang Beihang University The Department of Automation Science and Electrical Engineering Beijing100191 China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Advanced Institute of Information Technology Peking University Hangzhou310000 China

ISBN: (纸本)9789887581543

In this study, a multi-degree-of-freedom (Multi-DOF) robot (MDR) system based on a LightGBM-driven electroencephalogram (EEG) decoding model is designed and developed to assist subjects with hand motor dysfunction in their daily activities and neurorehabilitation. The system mainly consists of a motor imagery electroencephalogram (MI-EEG) evoking layer, an intention decoding layer, and an interaction executive layer. The MI-EEG evoking layer initially displays a virtual reality (VR) motion imagination scenario, instructing the subjects to imagine a real hand gripping movement, simultaneously collecting the electrical EEG signals and preprocessing the EEG signals. Secondly, in the intention decoding layer, a network combining temporal-spectral feature fusion and LightGBM (TSFF-LightGBM) for MI-BCI classification is used to more effectively boost brain decoding accuracy and decrease decoding time. Finally, in the interaction executive layer, the Multi-DOF wearable robot is developed to offer hand grasp motion kinesthetic feedback and visual feedback synced with MI. The following are the key benefits of the proposed MDR system: (1) We propose a new lightweight network structure more suitable for brain computer interface (BCI) interaction systems, achieving more accurate decoding and shorter identification time in different data sets, which helps to improve the practicability of the system and promote the practical clinical application of BCI rehabilitation technology. (2) We integrate BCI, VR, a wearable Multi-DOF robot, motion kinesthetic feedback, and visual feedback to improve human-machine interaction. Compared to the most recent investigations, the average accuracy of the MDR system on the publicly accessible datasets BCI IV 2a and HGD reached 75.89% and 93.53%, respectively. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Brain computer interface

CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding

学校读者我要写书评

暂无评论

arXiv 2023年

Learning representations through self-supervision on unlabeled data has proven highly effective for understanding diverse images. However, remote sensing images often have complex and densely populated scenes with multiple land objects and no clear foreground objects. This intrinsic property generates high object density, resulting in false positive pairs or missing contextual information in self-supervised learning. To address these problems, we propose a context-enhanced masked image modeling method (CtxMIM), a simple yet efficient MIM-based self-supervised learning for remote sensing image understanding. CtxMIM formulates original image patches as a reconstructive template and employs a Siamese framework to operate on two sets of image patches. A context-enhanced generative branch is introduced to provide contextual information through context consistency constraints in the reconstruction. With the simple and elegant design, CtxMIM encourages the pretraining model to learn object-level or pixel-level features on a large-scale dataset without specific temporal or geographical constraints. Finally, extensive experiments show that features learned by CtxMIM outperform fully supervised and state-of-the-art self-supervised learning methods on various downstream tasks, including land cover classification, semantic segmentation, object detection, and instance segmentation. These results demonstrate that CtxMIM learns impressive remote sensing representations with high generalization and transferability. Copyright © 2023, The Authors. All rights reserved.

关键词： Remote sensing

Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Dapeng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Qingdao Research Institute of Beihang University Qingdao China

Over the past few years, single-view 3D face reconstruction methods can produce beautiful 3D models. Nevertheless, the input of these works is unobstructed faces. We describe a system designed to reconstruct convincing face texture in the case of occlusion. Motivated by parsing facial features, we propose a complete face parsing map generation method guided by landmarks. We estimate the 2D face structure of the reasonable position of the occlusion area, which is used for the construction of 3D texture. An excellent anti-occlusion face reconstruction method should ensure the authenticity of the output, including the topological structure between the eyes, nose, and mouth. We extensively tested our method and its components, qualitatively demonstrating the rationality of our estimated facial structure. We conduct extensive experiments on general 3D face reconstruction tasks as concrete examples to demonstrate the method’s superior regulation ability over existing methods often break down. We further provide numerous quantitative examples showing that our method advances both the quality and the robustness of 3D face reconstruction under occlusion scenes. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D reconstruction

SA-BEV: Generating Semantic-Aware Bird’s-Eye-View Feature for Multi-view 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Jinqing Zhang, Yanan Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Recently, the pure camera-based Bird’s-Eye-View (BEV) perception provides a feasible solution for economical autonomous driving. However, the existing BEV-based multi-view 3D detectors generally transform all image features into BEV features, without considering the problem that the large proportion of background information may submerge the object information. In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features. Accordingly, we propose BEV-Paste, an effective data augmentation strategy that closely matches with semantic-aware BEV feature. In addition, we design a Multi-Scale Cross-Task (MSCT) head, which combines task-specific and cross-task information to predict depth distribution and semantic segmentation more accurately, further improving the quality of semantic-aware BEV feature. Finally, we integrate the above modules into a novel multi-view 3D object detection framework, namely SA-BEV. Experiments on nuScenes show that SA-BEV achieves state-of-the-art performance. Code has been available at https://***/mengtan00/***. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification

学校读者我要写书评

暂无评论

PHA: Patch-Wise High-Frequency Augmentation for Transformer-...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Guiwei Zhang Yongfei Zhang Tianyu Zhang Bo Li Shiliang Pu Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Pengcheng Laboratory Hikvision Research Institute

Although recent studies empirically show that injecting Convolutional Neural Networks (CNNs) into Vision Transformers (ViTs) can improve the performance of person reidentification, the rationale behind it remains elusive. From a frequency perspective, we reveal that ViTs perform worse than CNNs in preserving key high-frequency components (e.g, clothes texture details) since high-frequency components are inevitably diluted by low-frequency ones due to the intrinsic Self-Attention within ViTs. To remedy such inadequacy of the ViT, we propose a Patch-wise High-frequency Augmentation (PHA) method with two core designs. First, to enhance the feature representation ability of high-frequency components, we split patches with high-frequency components by the Discrete Haar Wavelet Transform, then empower the ViT to take the split patches as auxiliary input. Second, to prevent high-frequency components from being diluted by low-frequency ones when taking the entire sequence as input during network optimization, we propose a novel patch-wise contrastive loss. From the view of gradient optimization, it acts as an implicit augmentation to improve the representation ability of key high-frequency components. This benefits the ViT to capture key high-frequency components to extract discriminative person representations. PHA is necessary during training and can be removed during inference, without bringing extra complexity. Extensive experiments on widely-used ReID datasets validate the effectiveness of our method.

关键词：

Generative Landmarks Guided Eyeglasses Removal 3D Face Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

Single-view 3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the input is unobstructed faces which makes their method not suitable for in-the-wild conditions. We present a method for performing a 3D face that removes eyeglasses from a single image. Existing facial reconstruction methods fail to remove eyeglasses automatically for generating a photo-realistic 3D face"in-the-wild".The innovation of our method lies in a process for identifying the eyeglasses area robustly and remove it intelligently. In this work, we estimate the 2D face structure of the reasonable position of the eyeglasses area, which is used for the construction of 3D texture. An excellent anti-eyeglasses face reconstruction method should ensure the authenticity of the output, including the topological structure between the eyes, nose, and mouth. We achieve this via a deep learning architecture that performs direct regression of a 3DMM representation of the 3D facial geometry from a single 2D image. We also demonstrate how the related face parsing task can be incorporated into the proposed framework and help improve reconstruction quality. We conduct extensive experiments on existing 3D face reconstruction tasks as concrete examples to demonstrate the method’s superior regulation ability over existing methods often break down. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Yongchao Li, Shiwei Gao, Yingjie Huang, Ziyue Zhang, Yanan Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China Zhongguancun Laboratory Beijing China

Though feature-alignment based Domain Adaptive Object Detection (DAOD) methods have achieved remarkable progress, they ignore the source bias issue, i.e., the detector tends to acquire more source-specific knowledge, impeding its generalization capabilities in the target domain. Furthermore, these methods face a more formidable challenge in achieving consistent classification and localization in the target domain compared to the source domain. To overcome these challenges, we propose a novel Distillation-based Source Debiasing (DSD) framework for DAOD, which can distill domain-agnostic knowledge from a pre-trained teacher model, improving the detector's performance on both domains. In addition, we design a Target-Relevant Object Localization Network (TROLN), which can mine target-related localization information from source and target-style mixed data. Accordingly, we present a Domain-aware Consistency Enhancing (DCE) strategy, in which these information are formulated into a new localization representation to further refine classification scores in the testing stage, achieving a harmonization between classification and localization. Extensive experiments have been conducted to manifest the effectiveness of this method, which consistently improves the strong baseline by large margins, outperforming existing alignment-based works. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation