检索结果-内蒙古大学图书馆

MATE: Masked Autoencoders are Online 3D Test-Time Learners

学校读者我要写书评

暂无评论

MATE: Masked Autoencoders are Online 3D Test-Time Learners

International Conference on computer vision (ICCV)

作者： M. Jehanzeb Mirza Inkyu Shin Wei Lin Andreas Schriebl Kunyang Sun Jaesung Choe Mateusz Kozinski Horst Possegger In So Kweon Kuk-Jin Yoon Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Korea Advanced Institute of Science and Technology (KAIST) South Korea Southeast University China

Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT methods from the 2D image domain, MATE also leverages test data for adaptation. Its test-time objective is that of a Masked Autoencoder: a large portion of each test point cloud is removed before it is fed to the network, tasked with reconstructing the full point cloud. Once the network is updated, it is used to classify the point cloud. We test MATE on several 3D object classification datasets and show that it significantly improves robustness of deep networks to several types of corruptions commonly occurring in 3D point clouds. We show that MATE is very efficient in terms of the fraction of points it needs for the adaptation. It can effectively adapt given as few as 5% of tokens of each test sample, making it extremely lightweight. Our experiments show that MATE also achieves competitive performance by adapting sparsely on the test data, which further reduces its computational overhead, making it ideal for real-time applications.

关键词：

MATE: Masked Autoencoders are Online 3D Test-Time Learners

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mirza, M. Jehanzeb Shin, Inkyu Lin, Wei Schriebl, Andreas Sun, Kunyang Choe, Jaesung Possegger, Horst Kozinski, Mateusz Kweon, In So Yoon, Kuk-Jin Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Korea Republic of Southeast University China

关键词： Classification (of information)

Joint Optimization of Data Routing and Energy Cooperation for Broadcastive Wpt Assisted Data Collection in Wsns

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Jiang, Yang Gao, Zhenguo Wang, Yakai Xu, Qinglong Gan, Qiren Kaswan, Amar College of Computer Science and Technology in Huaqiao University Fujian Xiamen China Key Laboratory of Computer Vision Machine Learning of Fujian Province University Fujian Xiamen China Dhanbad India Hexagon Geosystems Services India Pvt. Ltd India

In Energy Harvesting assisted Wireless Sensor Networks (EH-WSNs), Wireless Power Transfer (WPT) technology plays a vital role in extending network lifespan by enabling energy cooperation among nodes. Nevertheless, existing energy cooperation assisted data collection methods mostly focused solely on Point-to-Point (P2P) style WPT, overlooking the broadcasting nature of wireless radio signals, which offers the potential for multiple nodes to harvest energy simultaneously from a single radio signal. To best exploit the broadcastive radio signals, this paper concentrates on harnessing broadcastive WPT-based energy cooperation for optimizing data collection performance in WSNs, and inspects the underlying joint optimization of Data Routing and Energy Cooperation for Data Collection (DREC-DC) problem. Here the term broadcastive WPT is used to distinguish from the P2P-style WPT considered in previous works. To overcome the scalability limitations of centralized solutions, we proposed an efficient Distributed method based on Projected Subgradient Algorithm (DPSA) by formulizing and transforming the single-slot version DREC-DC problem into a strict convex form. For situations where relevant information in some upcoming time slots are available ahead through predictions, DPSA is extended to a sliding window style multi-slot version. Our DPSA is compared with a P2P style energy cooperation approach and some classic routing algorithms not involving energy cooperation for assessing its effectiveness. Simulation results demonstrate that our distributive broadcastive-WPT based method leads to considerably higher data collection ability than others. © 2023, The Authors. All rights reserved.

关键词： Energy harvesting

Support-Query Prototype Fusion Network for Few-shot Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xiaoxiao Gao, Zhenguo Chen, Xiaowei Wang, Yakai Qu, Shulei Li, Na Department of Computer Science and Technology Huaqiao University No.668 Jimei Avenue Fujian Xiamen361021 China Department of Mechanical Engineering and Automation Huaqiao University No.668 Jimei Avenue Fujian Xiamen361021 China Key Laboratory of Computer Vision and Machine Learning Fujian Provincial Universities Fujian Xiamen361021 China

In recent years, deep learning based on Convolutional Neural Networks (CNNs) has achieved remarkable success in many applications. However, their heavy reliance on extensive labeled data and limited generalization ability to unseen classes pose challenges to their suitability for medical image processing tasks. Few-shot learning, which utilizes a small amount of labeled data to generalize to unseen classes, has emerged as a critical research area, attracting substantial attention. Currently, most studies employ a prototype-based approach, in which prototypical networks are used to construct prototypes from the support set, guiding the processing of the query set to obtain the final results. While effective, this approach heavily relies on the support set while neglecting the query set, resulting in notable disparities within the model classes. To mitigate this drawback, we propose a novel Support-Query Prototype Fusion Network (SQPFNet). SQPFNet initially generates several support prototypes for the foreground areas of the support images, thus producing a coarse segmentation mask. Subsequently, a query prototype is constructed based on the coarse segmentation mask, additionally exploiting pattern information in the query set. Thus, SQPFNet constructs highquality support-query fused prototypes, upon which the query image is segmented to obtain the final refined query mask. Evaluation results on two public datasets, SABS and CMR, show that SQPFNet achieves state-of-the-art performance. © 2024, CC BY.

关键词： Image segmentation

Video Test-Time Adaptation for Action Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lin, Wei Mirza, Muhammad Jehanzeb Kozinski, Mateusz Possegger, Horst Kuehne, Hilde Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Christian Doppler Laboratory for Embedded Machine Learning Goethe University Frankfurt Germany MIT-IBM Watson AI Lab United States

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models against common distribution shifts has so far not been demonstrated. We propose to address this problem with an approach tailored to spatio-temporal models that is capable of adaptation on a single video sample at a step. It consists in a feature distribution alignment technique that aligns online estimates of test set statistics towards the training statistics. We further enforce prediction consistency over temporally augmented views of the same test video sample. Evaluations on three benchmark action recognition datasets show that our proposed technique is architecture-agnostic and able to significantly boost the performance on both, the state of the art convolutional architecture TANet and the Video Swin Transformer. Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts. Code will be available at https://***/wlin-at/ViTTA. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

FAST3D: Flow-aware self-training for 3D object detectors

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fruhwirth-Reisinger, Christian Opitz, Michael Possegger, Horst Bischof, Horst Christian Doppler Laboratory for Embedded Machine Learning Institute of Computer Graphics and Vision Graz University of Technology

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g., geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method which enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker, that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art. © 2021, CC BY-NC-SA.

关键词： Object detection

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mirza, Muhammad Jehanzeb Micorek, Jakub Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria

Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we modify the feature representations of the model. We show that by sequentially adapting a model with only a fraction of unlabeled data, a strong performance gain can be achieved. With even less than 1% of unlabeled data from the target domain, DUA already achieves competitive results to strong baselines. In addition, the computational overhead is minimal in contrast to previous approaches. Our approach is simple, yet effective and can be applied to any architecture which uses batch normalization. We show the utility of DUA by evaluating it on a variety of domain adaptation datasets and tasks including object recognition, digit recognition and object detection. © 2021, CC BY.

关键词： Object recognition

Diffusion Posterior Proximal Sampling for Image Restoration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Hongjie He, Linchao Zhang, Mingqin Chen, Dongdong Luo, Kunming Luo, Mengting Zhou, Ji-Zhe Chen, Hu Lv, Jiancheng College of Computer Science Sichuan University Chengdu China National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu China Heriot-Watt University Edinburgh United Kingdom Hong Kong University of Science and Technology Hong Kong Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education China

Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources. Copyright © 2024, The Authors. All rights reserved.

关键词： White noise

An Efficient Domain-Incremental learning Approach to Drive in All Weather Conditions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mirza, Muhammad Jehanzeb Masana, Marc Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria TU Graz SAL Dependable Embedded Systems Lab Silicon Austria Labs Austria

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC - Domain Incremental through Statistical Correction - a simple online zero-forgetting approach which can incrementally learn new tasks (i.e. weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow. © 2022, CC BY.

关键词： Meteorology