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：

DRT: Detection Refinement for Multiple Object Tracking 32

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking

32nd British Machine vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

The Hololens In Medicine: A Systematic Review and Taxonomy

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gsaxner, Christina Li, Jianning Pepe, Antonio Jin, Yuan Kleesiek, Jens Schmalstieg, Dieter Egger, Jan Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria Institute of AI in Medicine University Medicine Essen Essen45131 Germany

The HoloLens (Microsoft Corp., Redmond, WA), a head-worn, optically see-through augmented reality display, is the main player in the recent boost in medical augmented reality research. In medical settings, the HoloLens enables the physician to obtain immediate insight into patient information, directly overlaid with their view of the clinical scenario, the medical student to gain a better understanding of complex anatomies or procedures, and even the patient to execute therapeutic tasks with improved, immersive guidance. In this systematic review, we provide a comprehensive overview of the usage of the first-generation HoloLens within the medical domain, from its release in March 2016, until the year of 2021, were attention is shifting towards it’s successor, the HoloLens 2. We identified 171 relevant publications through a systematic search of the PubMed and Scopus databases. We analyze these publications in regard to their intended use case, technical methodology for registration and tracking, data sources, visualization as well as validation and evaluation. We find that, although the feasibility of using the HoloLens in various medical scenarios has been shown, increased efforts in the areas of precision, reliability, usability, workflow and perception are necessary to establish AR in clinical practice. Copyright © 2022, The Authors. All rights reserved.

关键词： Taxonomies

Sparse Convolutional Neural Networks for Medical Image Analysis

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Li, Jianning Gsaxner, Christina Pepe, Antonio Schmalstieg, Dieter Kleesiek, Jens Egger, Jan Institute for Artificial Intelligence in Medicine Essen University Hospital Germany Institute of Computer Graphics and Vision Graz University of Technology Austria

Traditional convolutional neural network (CNN) methods rely on dense tensors, which makes them suboptimal for spatially sparse data. In this paper, we propose a CNN model based on sparse tensors for efficient processing of large and sparse medical images. In contrast to a dense CNN that takes the entire voxel grid as input, a sparse CNN processes only on the non-empty voxels, thus reducing the memory and computation overhead caused by the sparse input data. We evaluate our method on two clinically relevant skull reconstruction tasks: (1) given a defective skull, reconstruct the complete skull (i.e., skull shape completion), and (2) given a coarse skull, reconstruct a high-resolution skull with fine geometric details (shape super-resolution). Our method outperforms the state of the art in the skull reconstruction task quantitatively and qualitatively, while requiring substantially less memory for training and inference. We observed that, on the 3D skull data, the overall memory consumption of the sparse CNN grows approximately linearly during inference with respect to the image resolutions. During training, the memory usage remains clearly below increases in image resolution - an ×8 increase in voxel number leads to less than ×4 increase in memory requirements. Our study demonstrates the effectiveness of using a sparse CNN for skull reconstruction tasks, and our findings can be applied to other spatially sparse problems. We proof this by additional experimental results on other sparse medical datasets, like the aorta and the heart. Project page at https://***/Jianningli/SparseCNN. © 2022, CC BY.

关键词： Convolutional neural networks

An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bogensperger, Lea Ehrhardt, Matthias J. Pock, Thomas Salehi, Mohammad Sadegh Wong, Hok Shing Department of Quantitative Biomedicine University of Zurich Zurich8057 Switzerland Department of Mathematical Sciences University of Bath BathBA2 7AY United Kingdom Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria

We consider a bilevel learning framework for learning linear operators. In this framework, the learnable parameters are optimized via a loss function that also depends on the minimizer of a convex optimization problem (denoted lower-level problem). We utilize an iterative algorithm called ‘piggyback’ to compute the gradient of the loss and minimizer of the lower-level problem. Given that the lower-level problem is solved numerically, the loss function and thus its gradient can only be computed inexactly. To estimate the accuracy of the computed hypergradient, we derive an a-posteriori error bound, which provides guides for setting the tolerance for the lower-level problem, as well as the piggyback algorithm. To efficiently solve the upper-level optimization, we also propose an adaptive method for choosing a suitable step-size. To illustrate the proposed method, we consider a few learned regularizer problems, such as training an input-convex neural network. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

MCTS with Refinement for Proposals Selection Games in Scene Understanding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Stekovic, Sinisa Rad, Mahdi Moradi, Alireza Fraundorfer, Friedrich Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Université Paris-Est École des Ponts ParisTech Paris France

We propose a novel method applicable in many scene understanding problems that adapts the Monte Carlo Tree Search (MCTS) algorithm, originally designed to learn to play games of high-state complexity. From a generated pool of proposals, our method jointly selects and optimizes proposals that minimize the objective term. In our first application for floor plan reconstruction from point clouds, our method selects and refines the room proposals, modelled as 2D polygons, by optimizing on an objective function combining the fitness as predicted by a deep network and regularizing terms on the room shapes. We also introduce a novel differentiable method for rendering the polygonal shapes of these proposals. Our evaluations on the recent and challenging Structured3D and Floor-SP datasets show significant improvements over the state-of-the-art, without imposing hard constraints nor assumptions on the floor plan configurations. In our second application, we extend our approach to reconstruct general 3D room layouts from a color image and obtain accurate room layouts. We also show that our differentiable renderer can easily be extended for rendering 3D planar polygons and polygon embeddings. Our method shows high performance on the Matterport3D-Layout dataset, without introducing hard constraints on room layout configurations. Copyright © 2022, The Authors. All rights reserved.

关键词： Floors

SAILOR: Scaling Anchors via Insights into Latent Object Representation

学校读者我要写书评

暂无评论

arXiv 2022年

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

LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes vary heavily between domains due to, for instance, different labeling policies or geographical locations. State-of-the-art unsupervised domain adaptation approaches outsource methods to overcome the object size bias. Mainstream size adaptation approaches exploit target domain statistics, contradicting the original unsupervised assumption. Our novel unsupervised anchor calibration method addresses this limitation. Given a model trained on the source data, we estimate the optimal target anchors in a completely unsupervised manner. The main idea stems from an intuitive observation: by varying the anchor sizes for the target domain, we inevitably introduce noise or even remove valuable object cues. The latent object representation, perturbed by the anchor size, is closest to the learned source features only under the optimal target anchors. We leverage this observation for anchor size optimization. Our experimental results show that, without any retraining, we achieve competitive results even compared to state-of-the-art weakly-supervised size adaptation approaches. In addition, our anchor calibration can be combined with such existing methods, making them completely unsupervised. © 2022, CC BY.

关键词： Anchors

End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB

学校读者我要写书评

暂无评论

End-to-end Trainable Deep Neural Network for Robotic Grasp D...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Stefan Ainetter Friedrich Fraundorfer Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

In this work, we introduce a novel, end-to-end trainable CNN-based architecture to deliver high quality results for grasp detection suitable for a parallel-plate gripper, and semantic segmentation. Utilizing this, we propose a novel refinement module that takes advantage of previously calculated grasp detection and semantic segmentation and further increases grasp detection accuracy. Our proposed network delivers state-of-the-art accuracy on two popular grasp dataset, namely Cornell and Jacquard. As additional contribution, we provide a novel dataset extension for the OCID dataset, making it possible to evaluate grasp detection in highly challenging scenes. Using this dataset, we show that semantic segmentation can additionally be used to assign grasp candidates to object classes, which can be used to pick specific objects in the scene.

关键词： Deep learning Automation Conferences Semantics Feature extraction Convolutional neural networks Grippers

Quantum Transport in Open Spin Chains using Neural-Network Quantum States

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mellak, Johannes Arrigoni, Enrico Pock, Thomas von der Linden, Wolfgang Institute of Theoretical and Computational Physics Graz University of Technology Petersgasse 16/II GrazA-8010 Austria Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II GrazA-8010 Austria

In this work we study the treatment of asymmetric open quantum systems with neural-networks based on the restricted Boltzmann machine. In particular, we are interested in the non-equilibrium steady state current in the boundary-driven (anisotropic) Heisenberg spin chain. We address previously published difficulties in treating asymmetric dissipative systems with neural-network quantum states and Monte-Carlo sampling and present an optimization method and a sampling technique that can be used to obtain high-fidelity steady state approximations of such systems. We point out some inherent symmetries of the Lindblad operator under consideration and exploit them during sampling. We show that local observables are not always a good indicator of the quality of the approximation and finally present results for the spin current that are in agreement with known results of simple open Heisenberg chains. Copyright © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods