检索结果-内蒙古大学图书馆

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Stiffness-based Offline Toolpath Error Compensation for Robotized Incremental Forming

学校读者我要写书评

暂无评论

Stiffness-based Offline Toolpath Error Compensation for Robo...

Automation, Control and Robots (ICACR), International Conference on

作者： Walid K. Shaker Alexandr Klimchik Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Lincoln Centre for Autonomous Systems Research (L-CAS) School of Computer Science University of Lincoln Lincoln United Kingdom

This paper addresses the challenge of the poor accuracy and the toolpath deviation in Incremental Sheet Forming (ISF) caused by the forming forces applied to the workpiece. The paper proposes an offline toolpath error compensation approach based on stiffness analysis. A truncated cone was used as a test case and the numerical simulation of the ISF process was conducted on Abaqus CAE software to extract forming forces corresponding to toolpath points. The compensation algorithm is based on the Virtual Joint Method (VJM) and is implemented on a FANUC R-2000iC/165F robot using RoboDK API for MATLAB. The results show that the deviation of the robot tool due to the forming forces may reach up to 20 mm which can be handled by the compensated toolpath. Finally, the study proposes an overall process for the stiffness-based correction algorithm.

关键词：

Comparative Analysis of Springback Compensation for Various Profiles in Incremental Forming

学校读者我要写书评

暂无评论

Comparative Analysis of Springback Compensation for Various ...

International Russian Automation Conference (RusAutoCon)

Incremental forming encounters a common challenge known as the springback effect, wherein the workpiece undergoes elastic deformation and deviates slightly from the desired shape once the forming tool is released. This discrepancy between the intended and obtained shape results in reduced geometric accuracy, making incremental forming less precise compared to conventional methods. This research presents a novel springback effect compensation model for sheet forming processes. The main objective is to evaluate the model's performance across various profiles, with a focus on enhancing precision and accuracy in the formed shapes. The proposed model demonstrates an impressive ability to compensate for approximately 60% of the springback effect, offering a practical solution for offline springback compensation.

关键词：

DualQuat-LOAM: LiDAR Odometry and Mapping parametrized on Dual Quaternions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Velasco-Sánchez, Edison P. Recalde, Luis F. Li, Guanrui Candelas-Herias, Francisco A. Puente-Mendez, Santiago T. Torres-Medina, Fernando AUROVA Group of Automation Robotics and Computer Vision University of Alicante San Vicente del Raspeig S/N Alicante03690 Spain Worcester Polytechnic Institute Worcester01609 United States

This paper reports on a novel method for LiDAR odometry estimation, which completely parameterizes the system with dual quaternions. To accomplish this, the features derived from the point cloud, including edges, surfaces, and Stable Triangle Descriptor (STD), along with the optimization problem, are expressed in the dual quaternion set. This approach enables the direct combination of translation and orientation errors via dual quaternion operations, greatly enhancing pose estimation, as demonstrated in comparative experiments against other state-of-the-art methods. Our approach reduced drift error compared to other LiDAR-only-odometry methods, especially in scenarios with sharp curves and aggressive movements with large angular displacement. DualQuat-LOAM is benchmarked against several public datasets. In the KITTI dataset it has a translation and rotation error of 0.79% and 0.0039°/m, with an average run time of 53 ms. © 2024, CC BY-NC-ND.

关键词： robotics

FeCAM: exploiting the heterogeneity of class distributions in exemplar-free continual learning 23

学校读者我要写书评

暂无评论

FeCAM: exploiting the heterogeneity of class distributions i...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Dipam Goswami Yuyang Liu Bartłomiej Twardowski Joost van de Weijer Department of Computer Science Universitat Autònoma de Barcelona and Computer Vision Center Barcelona University of Chinese Academy of Sciences and State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences and Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Department of Computer Science Universitat Autònoma de Barcelona and Computer Vision Center Barcelona and IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM.

关键词：

Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Meraz, Md. Ansari, Md Afzal Javed, Mohammed Chakraborty, Pavan Center of Intelligent Robotics Lab Department of Information Technology Computer Vision & Biometrics Lab Department of Information Technology Indian Institute of Information Technology Allahabad U.P Prayagraj India

In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for classification tasks remains crucial. This paper presents Point-GR, a novel deep learning architecture designed explicitly to transform unordered raw point clouds into higher dimensions while preserving local geometric features. It introduces residual-based learning within the network to mitigate the point permutation issues in point cloud data. The proposed Point-GR network significantly reduced the number of network parameters in Classification and PartSegmentation compared to baseline graph-based networks. Notably, the Point-GR model achieves a state-of-the-art scene segmentation mean IoU of 73.47% on the S3DIS benchmark dataset, showcasing its effectiveness. Furthermore, the model shows competitive results in Classification and Part-Segmentation tasks. © 2024, CC BY.

关键词： Graph neural networks

LiCAR: pseudo-RGB LiDAR image for CAR segmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： de Loyola Páez-Ubieta, Ignacio Velasco-Sánchez, Edison P. Puente, Santiago T. AUtomatics RObotics and Artificial Vision Lab IUII: University Institute for Computer Research University of Alicante Crta. San Vicente s/n San Vicente del Raspeig AlicanteE-03690 Spain

With the advancement of computing resources, an increasing number of Neural Networks (NNs) are appearing for image detection and segmentation appear. However, these methods usually accept as input a RGB 2D image. On the other side, Light Detection And Ranging (LiDAR) sensors with many layers provide images that are similar to those obtained from a traditional low resolution RGB camera. Following this principle, a new dataset for segmenting cars in pseudo-RGB images has been generated. This dataset combines the information given by the LiDAR sensor into a Spherical Range Image (SRI), concretely the reflectivity, near infrared and signal intensity 2D images. These images are then fed into instance segmentation NNs. These NNs segment the cars that appear in these images, having as result a Bounding Box (BB) and mask precision of 88% and 81.5% respectively with You Only Look Once (YOLO)-v8 large. By using this segmentation NN, some trackers have been applied so as to follow each car segmented instance along a video feed, having great performance in real world experiments. © 2025, CC BY.

关键词： Image segmentation

Preliminary Study on Slack-Free Model Predictive Control of Twisted String-Based Antagonistic Joints

学校读者我要写书评

暂无评论

Preliminary Study on Slack-Free Model Predictive Control of ...

2020 International Conference Nonlinearity, Information and robotics, NIR 2020

作者： Balakhnov, Oleg Nedelchev, Simeon Gaponov, Igor Innopolis University Institute of Robotics and Computer Vision Innopolis Russia

ISBN: (纸本)9781728187631

In this work, we propose a model predictive controller (MPC) for simultaneous position and tension tracking in twisted string actuator-based antagonistic joints. The proposed controller takes into account unidirectional nature of the cables and minimize trajectory tracking error as well as control effort. The approach has been evaluated numerically in a series of simulations that demonstrated its feasibility and highlighted its advantage over the unconstrained controller, with position tracking accuracy improved by a factor of 10. The proposed MPC can be generalized and serve as the starting point for antagonistic control in multiple-degree-of-freedom systems based on twisted string actuators. © 2020 IEEE.

关键词： Actuators

Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition

学校读者我要写书评

暂无评论

Shift from Texture-bias to Shape-bias: Edge Deformation-base...

International Conference on computer vision (ICCV)

作者： Xilin He Qinliang Lin Cheng Luo Weicheng Xie Siyang Song Feng Liu Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institue of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing University of Leicester

Recent studies have shown the vulnerability of CNNs under perturbation noises, which is partially caused by the reason that the well-trained CNNs are too biased toward the object texture, i.e., they make predictions mainly based on texture cues. To reduce this texture-bias, current studies resort to learning augmented samples with heavily perturbed texture to make networks be more biased toward relatively stable shape cues. However, such methods usually fail to achieve real shape-biased networks due to the insufficient diversity of the shape cues. In this paper, we propose to augment the training dataset by generating semantically meaningful shapes and samples, via a shape deformation-based online augmentation, namely as SDbOA. The samples generated by our SDbOA have two main merits. First, the augmented samples with more diverse shape variations enable networks to learn the shape cues more elaborately, which encourages the network to be shape-biased. Second, semantic-meaningful shape-augmentation samples could be produced by jointly regularizing the generator with object texture and edge-guidance soft constraint, where the edges are represented more robustly with a self information guided map to better against the noises on them. Extensive experiments under various perturbation noises demonstrate the obvious superiority of our shape-bias-motivated model over the state of the arts in terms of robustness performance. Code is available at https://***/C0notSilly/-ICCV-23-Edge-Deformation-based-Online-Augmentation.

关键词：