检索结果-内蒙古大学图书馆

A general framework for lifelong localization and mapping in changing environment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Min Guo, Xin Song, Le Qin, Baoxing Shi, Xuesong Lee, Gim Hee Sun, Guanghui Gaussian Robotics Shanghai China Intel Labs China Beijing China Computer Vision and Robotic Perception Lab Department of Computer Science School of Computing National University of Singapore Singapore Singapore Department of Control Science and Engineering Harbin Institute of Technology China

The environment of most real-world scenarios such as malls and supermarkets changes at all times. A prebuilt map that does not account for these changes becomes out-of-date easily. Therefore, it is necessary to have an up-todate model of the environment to facilitate long-term operation of a robot. To this end, this paper presents a general lifelong simultaneous localization and mapping (SLAM) framework. Our framework uses a multiple session map representation, and exploits an efficient map updating strategy that includes map building, pose graph refinement and sparsification. To mitigate the unbounded increase of memory usage, we propose a maptrimming method based on the Chow-Liu maximum-mutualinformation spanning tree. The proposed SLAM framework has been comprehensively validated by over a month of robot deployment in real supermarket environment. Furthermore, we release the dataset collected from the indoor and outdoor changing environment with the hope to accelerate lifelong SLAM research in the community. Our dataset is available at https://***/sanduan168/lifelong-SLAM-dataset. © 2021, CC BY.

关键词： Retail stores

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Mengzhe Wang, Yali Wu, Jiaxi Wang, Yiru Li, Hanqing Li, Bo Gan, Weihao Wu, Wei Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China SenseTime Research University of Chinese Academy of Science China Shanghai AI Laboratory Shanghai China Beihang University China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. Our code and model will be available at here. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Human gait state prediction using cellular automata and classification using ELM

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Semwal, Vijay Bhaskar Gaud, Neha Nandi, G.C. Department of CSE Indian Insitute of Inforamtion technology Karnataka Dharwad India Institute Of Computer Science Vikram University Ujjain M.P. India Robotics & AI Lab Indian Insitute of Inforamtion Technology U.P. Allahabad India

In this research article, we have reported periodic cellular automata rules for different gait state prediction and classification of the gait data using extreme machine Leaning (ELM). This research is the first attempt to use cellular automaton to understand the complexity of bipedal walk. Due to non-linearity, varying configurations throughout the gait cycle and the passive joint located at the unilateral foot-ground contact in bipedal walk resulting variation of dynamic descriptions and control laws from phase to phase for human gait is making difficult to predict the bipedal walk states. We have designed the cellular automata rules which will predict the next gait state of bipedal steps based on the previous two neighbour states. We have designed cellular automata rules for normal walk. The state prediction will help to correctly design the bipedal walk. The normal walk depends on next two states and has total 8 states. We have considered the current and previous states to predict next state. So we have formulated 16 rules using cellular automata, 8 rules for each leg. The priority order maintained using the fact that if right leg in swing phase then left leg will be in stance phase. To validate the model we have classified the gait Data using ELM [1] and achieved accuracy 60%. We have explored the trajectories and compares with another gait trajectories. Finally we have presented the error analysis for different joints. Copyright © 2021, The Authors. All rights reserved.

关键词： Cellular automata

UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Jiayi Chen, Zan Ji, Yingrui Zhang, Liyun Luo, Daqin Li, Zhigang Shen, Yiqin Glasgow College University of Electronic Science and Technology of China Chengdu China School of Engineering University of Glasgow Glasgow United Kingdom Toursun Synbio Shanghai China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Research Institute Ubtech Robotics Corp Shenzhen China Qiyuan Lab. Beijing China Department of Computer Science Johns Hopkins University MD United States

Automated Machine Learning (AutoML) can streamline the complexities of machine learning pipelines. However, existing AutoML frameworks focus on discriminative tasks leaving generative tasks unexplored. Moreover, existing AutoML frameworks often lack interpretability and user engagement during the model development and training process, due to the absence of human-centered designs. To address these challenges, we propose UniAutoML, a human-centered AutoML framework that leverages Large Language Models (LLMs) to unify the automation of both discriminative (e.g., Transformers and CNNs for classification or regression) and generative tasks (e.g., fine-tuning diffusion models or LLMs). UniAutoML enables natural language interactions between users and the framework to provide real-time feedback and progress updates, thus enhancing the interpretability, transparency, and user control, where users can seamlessly modify or refine the model training in response to evolving needs. To ensure the safety and reliability of LLM-generated content, UniAutoML incorporates a safety guard-line that filter inputs and censor outputs. We evaluated UniAutoML’s performance and usability through experiments conducted on eight diverse datasets and user studies involving 25 participants. Our results demonstrate that UniAutoML not only achieves higher performance but also improves user control and trust in the AutoML process, which makes ML more accessible and intuitive for a broader audience. The code for UniAutoML is available at: https://***/richarf22/UniAutoML. © 2024, CC BY.

关键词： Digital elevation model

Conditional Sequential Modulation for Efficient Global Image Retouching 16th

学校读者我要写书评

暂无评论

Conditional Sequential Modulation for Efficient Global Image...

16th European Conference on computer Vision, ECCV 2020

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT - SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030586003

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1 × 1 convolution, CSRNet only contains less than 37 k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://***/hejingwenhejingwen/CSRNet. © 2020, Springer Nature Switzerland AG.

关键词： Pixels

Efficient Image Super-Resolution Using Pixel Attention 16th

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution Using Pixel Attention

Workshops held at the 16th European Conference on computer Vision, ECCV 2020

作者： Zhao, Hengyuan Kong, Xiangtao He, Jingwen Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030670696

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one—SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its two-branch architecture and attention scheme. While the second one—U-PA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model—PAN could achieve similar performance as the lightweight networks—SRResNet and CARN, but with only 272K parameters (17.92% of SRResNet and 17.09% of CARN). The effectiveness of each proposed component is also validated by ablation study. The code is available at https://***/zhaohengyuan1/PAN. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

Investigate indistinguishable points in semantic segmentation of 3D point cloud

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Mingye Zhou, Zhipeng Zhang, Junhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China Shanghai AI Lab Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures but different categories, and points in isolate small hard areas, which largely harm the performance of 3D semantic segmentation. To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which selects indistinguishable points adaptively by utilizing the hierarchical semantic features and enhance fine-grained features for points especially those indistinguishable points. We also introduce multi-stage loss to improve the feature representation in a progressive way. Moreover, in order to analyze the segmentation performances of indistinguishable areas, we propose a new evaluation metric called Indistinguishable Points Based Metric (IPBM). Our IAF-Net achieves the comparable results with state-of-the-art performance on several popular 3D point cloud datasets e.g. S3DIS and ScanNet, and clearly outperforms other methods on IPBM. Our code will be available at https://***/MingyeXu/IAF-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

Discovery of crime event sequences with constricted spatio-temporal sequential patterns

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Maciąg, Piotr S. Bembenik, Robert Dubrawski, Artur Warsaw University of Technology Institute of Computer Science Nowowiejska 15/19 Warsaw00-665 Poland Carnegie Mellon University Auton Lab The Robotics Institute 5000 Forbes Avenue PittsburghPA15213 United States

In this article, we introduce a novel type of spatio-temporal sequential patterns called Constricted Spatio-Temporal Sequential (CSTS) patterns and thoroughly analyze their properties. We demonstrate that the set of CSTS patterns is a concise representation of all spatio-temporal sequential patterns that can be discovered in a given dataset. To measure significance of the discovered CSTS patterns we adapt the participation index measure. We also provide CSTS-Miner: an algorithm that discovers all participation index strong CSTS patterns in event data. We experimentally evaluate the proposed algorithms using two crime-related datasets: Pittsburgh Police Incident Blotter Dataset and Boston Crime Incident Reports Dataset. In the experiments, the CSTS-Miner algorithm is compared with the other four state-of-the-art algorithms: STS-Miner, CSTPM, STBFM and CST-SPMiner. As the results of experiments suggest, the proposed algorithm discovers much fewer patterns than the other selected algorithms. Finally, we provide the examples of interesting crime-related patterns discovered by the proposed CSTS-Miner algorithm. Copyright © 2021, The Authors. All rights reserved.

关键词： Crime

Electrical frequency discrimination by fungi Pleurotus ostreatus

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Przyczyna, Dawid Szacilowski, Konrad Chiolerio, Alessandro Adamatzky, Andrew Academic Centre for Materials and Nanotechnology AGH University of Science and Technology Krakow Poland Istituto Italiano di Tecnologia Center for Converging Technologies Soft Bioinspired Robotics Via Morego 30 Genova16165 Italy Unconventional Computing Lab UWE Bristol United Kingdom Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece

We stimulate mycelian networks of oyster fungi Pleurotus ostreatus with low frequency sinusoidal electrical signals. We demonstrate that the fungal networks can discriminate between frequencies in a fuzzy or threshold based manner. Details about the mixing of frequencies by the mycelium networks are provided. The results advance the novel field of fungal electronics and pave ground for the design of living, fully recyclable, electron devices. Copyright © 2022, The Authors. All rights reserved.

关键词： Fungi