检索结果-内蒙古大学图书馆

Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Zeyang Xue, Qilong He, Yuhang Bai, Yifan Wei, Xing Gong, Yihong Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China School of Software Engineering Xi’an Jiaotong University China

This paper introduces the point-axis representation for oriented object detection, as depicted in aerial images in Figure 1, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Activation Template Matching Loss for Explainable Face Recognition 17

学校读者我要写书评

暂无评论

Activation Template Matching Loss for Explainable Face Recog...

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Lin, Huawei Liu, Haozhe Li, Qiufu Shen, Linlin Computer Vision Institute School of Computer Science and Softwre Enginnering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (纸本)9798350345445

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss. © 2023 IEEE.

关键词： Face recognition

Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mosbach, Malte Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI - Intelligent Systems and Robotics The Center for Robotics The Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

Interactive grasping from clutter, akin to human dexterity, is one of the longest-standing problems in robot learning. Challenges stem from the intricacies of visual perception, the demand for precise motor skills, and the complex interplay between the two. In this work, we present Teacher-Augmented Policy Gradient (TAPG), a novel two-stage learning framework that synergizes reinforcement learning and policy distillation. After training a teacher policy to master the motor control based on object pose information, TAPG facilitates guided, yet adaptive, learning of a sensorimotor policy, based on object segmentation. We zero-shot transfer from simulation to a real robot by using Segment Anything Model for promptable object segmentation. Our trained policies adeptly grasp a wide variety of objects from cluttered scenarios in simulation and the real world based on human-understandable prompts. Furthermore, we show robust zero-shot transfer to novel objects. Videos of our experiments are available at https://***/grasp_anything. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

Saturated Robust Nonlinear Control for Double-Pendulum Quadrotor Transportation Systems

学校读者我要写书评

暂无评论

Saturated Robust Nonlinear Control for Double-Pendulum Quadr...

第42届中国控制会议

作者： Chen Su Yuxuan Chen Hai Yu Xiao Liang Jianda Han Yongchun Fang Institute of Robotics and Automatic Information System College of Artificial Intelligence Tianjin Key Laboratory of Intelligent RoboticsNankai University

Unknown external disturbances and dynamic/parameter uncertainties are usually existing when the quadrotor transportation system performs cargo delivery missions in the actual environment. Additionally, in most researches, the hook and the payload are regarded as a single point of mass which ignore the double-pendulum effect. To address the aforementioned issues, this paper proposed a saturated robust nonlinear controller for the quadrotor transportation system with double-pendulum effect, which has the ability to handle the lumped disturbance and suppress the payload and hook swing angles. On the basis of Lyapunov techniques and LaSalle's Invariance Theorem, the asymptotic convergence of the closed-loop system is *** results are presented to verify the performance of the designed control scheme.

关键词：

Epipolar Attention Field Transformers for Bird’s Eye View Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Witte, Christian Behley, Jens Stachniss, Cyrill Raaijmakers, Marvin CARIAD SE Germany Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular, approaches extracting a bird’s eye view (BEV) from multiple cameras have demonstrated great performance for spatial understanding. This paper addresses the dependency on learned positional encodings to correlate image and BEV feature map elements for transformer-based methods. We propose leveraging epipolar geometric constraints to model the relationship between cameras and the BEV by Epipolar Attention Fields. They are incorporated into the attention mechanism as a novel attribution term, serving as an alternative to learned positional encodings. Experiments show that our method EAFormer outperforms previous BEV approaches by 2% mIoU for map semantic segmentation and exhibits superior generalization capabilities compared to implicitly learning the camera configuration. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Helin Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI – Intelligent Systems and Robotics The Center for Robotics The Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle’s surroundings. However, such systems struggle to perceive occluded areas and gaps in the scene due to the sparsity of these point clouds and their lack of semantics. To address these challenges, Semantic Scene Completion (SSC) jointly predicts unobserved geometry and semantics in the scene given raw LiDAR measurements, aiming for a more complete scene representation. Building on promising results of diffusion models in image generation and super-resolution tasks, we propose their extension to SSC by implementing the noising and denoising diffusion processes in the point and semantic spaces individually. To control the generation, we employ semantic LiDAR point clouds as conditional input and design local and global regularization losses to stabilize the denoising process. We evaluate our approach on autonomous driving datasets and our approach outperforms the state-of-the-art for SSC. © 2024, CC BY.

关键词： Semantics

ICE-SEARCH: A LANGUAGE MODEL-DRIVEN FEATURE SELECTION APPROACH

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Tianze Yang, Tianyi Lyu, Fuyuan Liu, Shaoshan Liu, Xue School of Computer Science McGill University Canada MILA Canada Shenzhen Institute of Artificial Intelligence and Robotics for Society China

This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, which is among the first works that melds large language models (LLMs) with evolutionary algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications. ICE-SEARCH harnesses the crossover and mutation capabilities inherent in LLMs within an evolutionary framework, significantly improving FS through the model's comprehensive world knowledge and its adaptability to a variety of roles. Our evaluation of this methodology spans three crucial MPA tasks: stroke, cardiovascular disease, and diabetes, where ICE-SEARCH outperforms traditional FS methods in pinpointing essential features for medical applications. ICE-SEARCH achieves State-of-the-Art (SOTA) performance in stroke prediction and diabetes prediction;the Decision-Randomized ICE-SEARCH ranks as SOTA in cardiovascular disease prediction. The study emphasizes the critical role of incorporating domain-specific insights, illustrating ICE-SEARCH's robustness, generalizability, and convergence. This opens avenues for further research into comprehensive and intricate FS landscapes, marking a significant stride in the application of artificial intelligence in medical predictive analytics. Copyright © 2024, The Authors. All rights reserved.

关键词： Predictive analytics

Fast Global Point Cloud Registration using Semantic NDT

学校读者我要写书评

暂无评论

Fast Global Point Cloud Registration using Semantic NDT

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Robert Schirmer Narunas Vaskevicius Peter Biber Cyrill Stachniss Robert Bosch GmbH Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Robust and accurate point cloud registration is an essential part of many robotic tasks such as SLAM or object pose retrieval. In this paper, we address the problem of global 3D point cloud registration, i.e., the task of estimating the 3D rigid body transform between a source and a target point cloud without any initial guess. Typically, the problem is solved by extracting and matching features to find a data association and then computing a transform that minimizes the squared distance between points. Our approach combines the normal distributions transform and oriented point pair framework and introduces the NDT distance histogram to quickly generate and test candidate transforms. Our method further exploits semantic information if available for greater speed. We implement our algorithm in C++ and compare it to other state-of-the-art approaches on a diverse set of environments. Our evaluation shows that our method outperforms the other approaches, especially concerning run-time and compute efficiency.

关键词： Point cloud compression Location awareness Histograms Three-dimensional displays Simultaneous localization and mapping Semantic segmentation Semantics Transforms Feature extraction Intelligent robots

On Diffusion Process in SE(3)-invariant Space

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Zihan Liu, Ruiying Zheng, Jiachen Wang, Xiaoxue Yu, Tianshu The Chinese University of Hong Kong Shenzhen China Chemlex Poland Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)invariant properties can be naturally characterized by the inter-point distance manifold. However, due to the non-trivial geometry, we still lack a comprehensive understanding of the diffusion mechanism within such SE(3)-invariant space. This study addresses this gap by mathematically delineating the diffusion mechanism under SE(3)-invariance, via zooming into the interaction behavior between coordinates and the inter-point distance manifold through the lens of differential geometry. Upon this analysis, we propose accurate and projection-free diffusion SDE and ODE accordingly. Such formulations enable enhancing the performance and the speed of generation pathways;meanwhile offering valuable insights into other systems incorporating SE(3)-invariance. © 2024, CC BY.

关键词： Geometry