检索结果-内蒙古大学图书馆

A pushing-grasping collaborative method based on deep q-network algorithm in dual perspectives

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gang, Peng Jinhu, Liao Shangbin, Guan Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and covering, for the reason that can’t recognize objects accurately in cluster scenes from a single perspective and the manipulators can’t make the environment better for grasping. In this case, a novel method of pushing-grasping collaborative based on the deep Q-network in dual perspectives is proposed in this paper. This method adopts an improved deep Q-network algorithm, with an RGB-D camera to obtain the information of objects’ RGB images and point cloud from two perspectives, and combines the pushing and grasping actions, so that the trained manipulator can make the scenes better for grasping, so that it can perform well in more complicated grasping scenes. What’s more, we improved the reward function of the deep Q-network and propose the piecewise reward function to speed up the convergence of the deep Q-network. We trained different models and tried different methods in the V-REP simulation environment, and it drew a conclusion that the method proposed in this paper converges quickly and the success rate of grasping objects in unstructured scenes raises up to 83.5%. Besides, it shows the generalization ability and well performance when novel objects appear in the scenes that the manipulator has never grasped before. Copyright © 2021, The Authors. All rights reserved.

关键词： Manipulators

Exploring Stronger Feature for Temporal Action Localization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qing, Zhiwu Wang, Xiang Huang, Ziyuan Feng, Yutong Zhang, Shiwei Jiang, Jianwen Tang, Mingqian Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upper bound of detection performance. In this technical report, we explored classic convolution-based backbones and the recent surge of transformer-based backbones. We found that the transformer-based methods can achieve better classification performance than convolution-based, but they cannot generate accuracy action proposals. In addition, extracting features with larger frame resolution to reduce the loss of spatial information can also effectively improve the performance of temporal action localization. Finally, we achieve 42.42% in terms of mAP on validation set with a single SlowFast [9] feature by a simple combination: BMN [16]+TCANet [19], which is 1.87% higher than the result of 2020 [20]’s multi-model ensemble. Finally, we achieve Rank 1st on the CVPR2021 HACS supervised Temporal Action Localization Challenge. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

A Multi-scale Network for Semantic Segmentation of 3D Point Clouds

学校读者我要写书评

暂无评论

A Multi-scale Network for Semantic Segmentation of 3D Point ...

Chinese Automation Congress (CAC)

作者： Ying He Li Xiao Yong Jiang Zhigang Sun Zhuo Wang Gang Peng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Semantic segmentation is a fundamental operation in scene analysis. In this paper, an effective multiscale network for 3D point cloud semantic segmentation was introduced. By using a multiscale local feature extraction module which composed of four feature extractors of different scales in parallel, the generalizability of network for complex structures is enhanced effectively. To adaptively learn important feature channels, an attention mechanism is designed. Combining multiple features through skip connection, the network can preferably assign the semantic label for every point by exploiting global and local features. Experiments on 3D dataset (S3DIS) verify that our network is able to learn local region features, and the results are superior or comparable to the state-of-the-art.

关键词： Feature extraction Three-dimensional displays Semantics Two dimensional displays Intelligent control Image processing Automation

Hierarchical Spatio-temporal Decoupling for Text-to- Video Generation

学校读者我要写书评

暂无评论

Hierarchical Spatio-temporal Decoupling for Text-to- Video G...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhiwu Qing Shiwei Zhang Jiayu Wang Xiang Wang Yujie Wei Yingya Zhang Changxin Gao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Alibaba Group Fudan University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial content and temporal dynamics together, leading to a notably increased complexity of text-to-video generation (T2V). In this work, we propose HiGen, a diffusion model-based method that improves performance by decoupling the spatial and temporal factors of videos from two perspectives, i.e., structure level and content level. At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser. Specifically, we generate spatially coherent priors using text during spatial reasoning and then generate temporally coherent motions from these priors during temporal reasoning. At the content level, we extract two subtle cues from the content of the input video that can express motion and appearance changes, respectively. These two cues then guide the model's training for generating videos, enabling flexible content variations and enhancing temporal stability. Through the decoupled paradigm, HiGen can effectively reduce the complexity of this task and generate realistic videos with semantics accuracy and motion stability. Extensive experiments demonstrate the superior performance of HiGen over the state-of-the-art T2V methods. We have released our source code and models.

关键词： Training Source coding Semantics Spatial coherence Cognition Stability analysis Complexity theory

MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Gao, Changxin Zhang, Yingya Zhao, Deli Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure between local frames tends to be inaccurate due to the lack of guidance to force long-range temporal perception;ii) explicit motion learning is usually ignored, leading to partial information loss. To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder. Specifically, the long-short contrastive objective is to endow local frame features with long-form temporal awareness by maximizing their agreement with the global token of videos belonging to the same class. The motion autodecoder is a lightweight architecture to reconstruct pixel motions from the differential features, which explicitly embeds the network with motion dynamics. By this means, MoLo can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching. To demonstrate the effectiveness, we evaluate MoLo on five standard benchmarks, and the results show that MoLo favorably outperforms recent advanced methods. The source code is available at https://***/alibaba-mmai-research/MoLo. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Semi-Supervised Generalized Source-Free Domain Adaptation (SSG-SFDA)

学校读者我要写书评

暂无评论

Semi-Supervised Generalized Source-Free Domain Adaptation (S...

International Joint Conference on Neural Networks (IJCNN)

作者： Jiayu An Changming Zhao Dongrui Wu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Continual learning aims to learn on a sequence of new tasks while maintaining the performance on previous tasks. Source-free domain adaptation (SFDA), which adapts a pretrained source model to a target domain, is useful in protecting the source domain data privacy. Generalized SFDA (G-SFDA) combines continual learning and SFDA to achieve outstanding performance on both the source and the target domains. This paper proposes semi-supervised G-SFDA (SSG-SFDA) for domain incremental learning, where a pre-trained source model (instead of the source data), few labeled target data, and plenty of unlabeled target data, are available. The goal is to achieve good performance on all domains. To cope with domain-ID agnostic, SSG-SFDA trains a conditional variational auto-encoder (CVAE) for each domain to learn its feature distribution, and a domain discriminator using virtual shallow features generated by CVAE to estimate the domain ID. To cope with catastrophic forgetting, SSG-SFDA uses soft domain attention to improve the sparse domain attention in G-SFDA. To cope with insufficient labeled target data, SSG-SFDA uses MixMatch to augment the unlabeled target data and better exploit the few labeled target data. Experiments on three datasets demonstrated the effectiveness of SSG-SFDA.

关键词：

Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Ziang Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

—In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approach for reducing this data labeling effort. It optimally selects the best few samples to label, so that a better machine learning model can be trained from the same number of labeled samples. This paper considers active learning for regression (ALR) problems. Three essential criteria – informativeness, representativeness, and diversity – have been proposed for ALR. However, very few approaches in the literature have considered all three of them simultaneously. We propose three new ALR approaches, with different strategies for integrating the three criteria. Extensive experiments on 12 datasets in various domains demonstrated their effectiveness. Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

Distributed second order sliding mode secondary frequency control for HVDC system

学校读者我要写书评

暂无评论

Distributed second order sliding mode secondary frequency co...

Chinese Automation Congress (CAC)

作者： Yang-Ming Dou Ming Chi Zhi-Wei Liu Key Laboratory of Image Processing and Intelligent Control Ministry of Education College of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

This paper studies the secondary frequency control among non-synchronous AC areas interconnected by High Voltage Direct Current (HVDC). A distributed second order sliding mode control scheme is adopted to secondary frequency control of HVDC transmission systems to adjust the frequency of power grid to rated value, which solves the frequency disturbance caused by load power change of the DC power grid. And on this basis, the power generation in each region is reasonably distributed, so as to minimize the cost of power generation. Finally, the stability of the system is proved on an appropriate sliding manifold.

关键词： Frequency control HVDC transmission Power system stability Economics Sliding mode control Power system dynamics Manifolds

When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo

学校读者我要写书评

暂无评论

When Epipolar Constraint Meets Non-local Operators in Multi-...

International Conference on Computer Vision (ICCV)

作者： Tianqi Liu Xinyi Ye Weiyue Zhao Zhiyu Pan Min Shi Zhiguo Cao Ministry of Education School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain nonlocal feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-toline search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is available at https://***/TQTQliu/ET-MVSNet.

关键词：