PyTorchKR Papers

최신 논문

총 194편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2207.01778

Object-Level Targeted Selection via Deep Template Matching

Retrieving images with objects that are semantically similar to objects of interest (OOI) in a query image has many practical use cases. A few examples include fixing failures like false negatives/positives of a learned model or mitigating class imbalance in a dataset. The targeted selection task requires finding the relevant data from a large-scale pool of unlabeled data. Manual mining at this scale is infeasible. Further, the OOI are often small and occupy less than 1% of image area, are occluded, and co-exist with many semantically different objects in cluttered scenes. Existing semantic image retrieval methods often focus on mining for larger sized geographical landmarks, and/or require extra labeled data, such as images/image-pairs with similar objects, for mining images with generic objects. We propose a fast and robust template matching algorithm in the DNN feature space, that retrieves semantically similar images at the object-level from a large unlabeled pool of data. We project the region(s) around the OOI in the query image to the DNN feature space for use as the template. This enables our method to focus on the semantics of the OOI without requiring extra labeled data. In the context of autonomous driving, we evaluate our system for targeted selection by using failure cases of object detectors as OOI. We demonstrate its efficacy on a large unlabeled dataset with 2.2M images and show high recall in mining for images with small-sized OOI. We compare our method against a well-known semantic image retrieval method, which also does not require extra labeled data. Lastly, we show that our method is flexible and retrieves images with one or more semantically different co-occurring OOI seamlessly.

arXiv:2207.02179

Activation Template Matching Loss for Explainable Face Recognition

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss.

arXiv:2207.01092

The Gesture Authoring Space: Authoring Customised Hand Gestures for Grasping Virtual Objects in Immersive Virtual Environments

Natural user interfaces are on the rise. Manufacturers for Augmented, Virtual, and Mixed Reality head mounted displays are increasingly integrating new sensors into their consumer grade products, allowing gesture recognition without additional hardware. This offers new possibilities for bare handed interaction within virtual environments. This work proposes a hand gesture authoring tool for object specific grab gestures allowing virtual objects to be grabbed as in the real world. The presented solution uses template matching for gesture recognition and requires no technical knowledge to design and create custom tailored hand gestures. In a user study, the proposed approach is compared with the pinch gesture and the controller for grasping virtual objects. The different grasping techniques are compared in terms of accuracy, task completion time, usability, and naturalness. The study showed that gestures created with the proposed approach are perceived by users as a more natural input modality than the others.

arXiv:2204.00477

Autonomous crater detection on asteroids using a fully-convolutional neural network

This paper shows the application of autonomous Crater Detection using the U-Net, a Fully-Convolutional Neural Network, on Ceres. The U-Net is trained on optical images of the Moon Global Morphology Mosaic based on data collected by the LRO and manual crater catalogues. The Moon-trained network will be tested on Dawn optical images of Ceres: this task is accomplished by means of a Transfer Learning (TL) approach. The trained model has been fine-tuned using 100, 500 and 1000 additional images of Ceres. The test performance was measured on 350 never before seen images, reaching a testing accuracy of 96.24%, 96.95% and 97.19%, respectively. This means that despite the intrinsic differences between the Moon and Ceres, TL works with encouraging results. The output of the U-Net contains predicted craters: it will be post-processed applying global thresholding for image binarization and a template matching algorithm to extract craters positions and radii in the pixel space. Post-processed craters will be counted and compared to the ground truth data in order to compute image segmentation metrics: precision, recall and F1 score. These indices will be computed, and their effect will be discussed for tasks such as automated crater cataloguing and optical navigation.

arXiv:2203.17234공식 코드 · Papers with Code

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

We present a method that can recognize new objects and estimate their 3D pose in RGB images even under partial occlusions. Our method requires neither a training phase on these objects nor real images depicting them, only their CAD models. It relies on a small set of training objects to learn local object representations, which allow us to locally match the input image to a set of "templates", rendered images of the CAD models for the new objects. In contrast with the state-of-the-art methods, the new objects on which our method is applied can be very different from the training objects. As a result, we are the first to show generalization without retraining on the LINEMOD and Occlusion-LINEMOD datasets. Our analysis of the failure modes of previous template-based approaches further confirms the benefits of local features for template matching. We outperform the state-of-the-art template matching methods on the LINEMOD, Occlusion-LINEMOD and T-LESS datasets. Our source code and data are publicly available at https://github.com/nv-nguyen/template-pose

arXiv:2203.15216공식 코드 · Papers with Code

Affine Medical Image Registration with Coarse-to-Fine Vision Transformer

Affine registration is indispensable in a comprehensive medical image registration pipeline. However, only a few studies focus on fast and robust affine registration algorithms. Most of these studies utilize convolutional neural networks (CNNs) to learn joint affine and non-parametric registration, while the standalone performance of the affine subnetwork is less explored. Moreover, existing CNN-based affine registration approaches focus either on the local misalignment or the global orientation and position of the input to predict the affine transformation matrix, which are sensitive to spatial initialization and exhibit limited generalizability apart from the training dataset. In this paper, we present a fast and robust learning-based algorithm, Coarse-to-Fine Vision Transformer (C2FViT), for 3D affine medical image registration. Our method naturally leverages the global connectivity and locality of the convolutional vision transformer and the multi-resolution strategy to learn the global affine registration. We evaluate our method on 3D brain atlas registration and template-matching normalization. Comprehensive results demonstrate that our method is superior to the existing CNNs-based affine registration methods in terms of registration accuracy, robustness and generalizability while preserving the runtime advantage of the learning-based methods. The source code is available at https://github.com/cwmok/C2FViT.

arXiv:2203.10035

SHREC 2021: Classification in cryo-electron tomograms

Cryo-electron tomography (cryo-ET) is an imaging technique that allows three-dimensional visualization of macro-molecular assemblies under near-native conditions. Cryo-ET comes with a number of challenges, mainly low signal-to-noise and inability to obtain images from all angles. Computational methods are key to analyze cryo-electron tomograms. To promote innovation in computational methods, we generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms. Our publicly available dataset contains ten tomographic reconstructions of simulated cell-like volumes. Each volume contains twelve different types of complexes, varying in size, function and structure. In this paper, we have evaluated seven different methods of finding and classifying proteins. Seven research groups present results obtained with learning-based methods and trained on the simulated dataset, as well as a baseline template matching (TM), a traditional method widely used in cryo-ET research. We show that learning-based approaches can achieve notably better localization and classification performance than TM. We also experimentally confirm that there is a negative relationship between particle size and performance for all methods.

arXiv:2203.09200

Novel Consistency Check For Fast Recursive Reconstruction Of Non-Regularly Sampled Video Data

Quarter sampling is a novel sensor design that allows for an acquisition of higher resolution images without increasing the number of pixels. When being used for video data, one out of four pixels is measured in each frame. Effectively, this leads to a non-regular spatio-temporal sub-sampling. Compared to purely spatial or temporal sub-sampling, this allows for an increased reconstruction quality, as aliasing artifacts can be reduced. For the fast reconstruction of such sensor data with a fixed mask, recursive variant of frequency selective reconstruction (FSR) was proposed. Here, pixels measured in previous frames are projected into the current frame to support its reconstruction. In doing so, the motion between the frames is computed using template matching. Since some of the motion vectors may be erroneous, it is important to perform a proper consistency checking. In this paper, we propose faster consistency checking methods as well as a novel recursive FSR that uses the projected pixels different than in literature and can handle dynamic masks. Altogether, we are able to significantly increase the reconstruction quality by + 1.01 dB compared to the state-of-the-art recursive reconstruction method using a fixed mask. Compared to a single frame reconstruction, an average gain of about + 1.52 dB is achieved for dynamic masks. At the same time, the computational complexity of the consistency checks is reduced by a factor of 13 compared to the literature algorithm.

arXiv:2203.08652공식 코드 · Papers with Code

Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow

Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed distance functions learned through deep neural nets. Recently DIFs-based methods have been proposed to handle shape reconstruction and dense point correspondences simultaneously, capturing semantic relationships across shapes of the same class by learning a DIFs-modeled shape template. These methods provide great flexibility and accuracy in reconstructing 3D shapes and inferring correspondences. However, the point correspondences built from these methods do not intrinsically preserve the topology of the shapes, unlike mesh-based template matching methods. This limits their applications on 3D geometries where underlying topological structures exist and matter, such as anatomical structures in medical images. In this paper, we propose a new model called Neural Diffeomorphic Flow (NDF) to learn deep implicit shape templates, representing shapes as conditional diffeomorphic deformations of templates, intrinsically preserving shape topologies. The diffeomorphic deformation is realized by an auto-decoder consisting of Neural Ordinary Differential Equation (NODE) blocks that progressively map shapes to implicit templates. We conduct extensive experiments on several medical image organ segmentation datasets to evaluate the effectiveness of NDF on reconstructing and aligning shapes. NDF achieves consistently state-of-the-art organ shape reconstruction and registration results in both accuracy and quality. The source code is publicly available at https://github.com/Siwensun/Neural_Diffeomorphic_Flow--NDF.

arXiv:2202.13347

A Robust Multimodal Remote Sensing Image Registration Method and System Using Steerable Filters with First- and Second-order Gradients

Co-registration of multimodal remote sensing images is still an ongoing challenge because of nonlinear radiometric differences (NRD) and significant geometric distortions (e.g., scale and rotation changes) between these images. In this paper, a robust matching method based on the Steerable filters is proposed consisting of two critical steps. First, to address severe NRD, a novel structural descriptor named the Steerable Filters of first- and second-Order Channels (SFOC) is constructed, which combines the first- and second-order gradient information by using the steerable filters with a multi-scale strategy to depict more discriminative structure features of images. Then, a fast similarity measure is established called Fast Normalized Cross-Correlation (Fast-NCCSFOC), which employs the Fast Fourier Transform technique and the integral image to improve the matching efficiency. Furthermore, to achieve reliable registration performance, a coarse-to-fine multimodal registration system is designed consisting of two pivotal modules. The local coarse registration is first conducted by involving both detection of interest points (IPs) and local geometric correction, which effectively utilizes the prior georeferencing information of RS images to address global geometric distortions. In the fine registration stage, the proposed SFOC is used to resist significant NRD, and to detect control points between multimodal images by a template matching scheme. The performance of the proposed matching method has been evaluated with many different kinds of multimodal RS images. The results show its superior matching performance compared with the state-of-the-art methods. Moreover, the designed registration system also outperforms the popular commercial software in both registration accuracy and computational efficiency. Our system is available at https://github.com/yeyuanxin110.

arXiv:2201.12805

Automatic Segmentation of Left Ventricle in Cardiac Magnetic Resonance Images

Segmentation of the left ventricle in cardiac magnetic resonance imaging MRI scans enables cardiologists to calculate the volume of the left ventricle and subsequently its ejection fraction. The ejection fraction is a measurement that expresses the percentage of blood leaving the heart with each contraction. Cardiologists often use ejection fraction to determine one's cardiac function. We propose multiscale template matching technique for detection and an elliptical active disc for automated segmentation of the left ventricle in MR images. The elliptical active disc optimizes the local energy function with respect to its five free parameters which define the disc. Gradient descent is used to minimize the energy function along with Green's theorem to optimize the computation expenses. We report validations on 320 scans containing 5,273 annotated slices which are publicly available through the Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac Segmentation (M&Ms) Challenge. We achieved successful localization of the left ventricle in 89.63% of the cases and a Dice coefficient of 0.873 on diastole slices and 0.770 on systole slices. The proposed technique is based on traditional image processing techniques with a performance on par with the deep learning techniques.

arXiv:2201.06098

An Edge Map based Ensemble Solution to Detect Water Level in Stream

Flooding is one of the most dangerous weather events today. Between $2015-2019$, on average, flooding has caused more than $130$ deaths every year in the USA alone. The devastating nature of flood necessitates the continuous monitoring of water level in the rivers and streams to detect the incoming flood. In this work, we have designed and implemented an efficient vision-based ensemble solution to continuously detect the water level in the creek. Our solution adapts template matching algorithm to find the region of interest by leveraging edge maps, and combines two parallel approach to identify the water level. While first approach fits a linear regression model in edge map to identify the water line, second approach uses a split sliding window to compute the sum of squared difference in pixel intensities to find the water surface. We evaluated the proposed system on $4306$ images collected between $3$rd October and $18$th December in 2019 with the frequency of $1$ image in every $10$ minutes. The system exhibited low error rate as it achieved $4.8$, $3.1\%$ and $0.92$ scores for MAE, MAPE and $R^2$ evaluation metrics, respectively. We believe the proposed solution is very practical as it is pervasive, accurate, doesn't require installation of any additional infrastructure in the water body and can be easily adapted to other locations.

arXiv:2201.00877

Gaussian-Hermite Moment Invariants of General Multi-Channel Functions

With the development of data acquisition technology, large amounts of multi-channel data are collected and widely used in many fields. Most of them, such as RGB images and vector fields, can be expressed as different types of multi-channel functions. Feature extraction of multi-channel data for identifying interest patterns is a critical but challenging task. This paper focuses on constructing moment-based features of general multi-channel functions. Specifically, we define two transform models, rotation-affine transform and total rotation transform, to describe real deformations of multi-channel data. Then, we design a structural framework to generate Gaussian-Hermite moment invariants for these two transform models systematically. It is the first time that a unified framework has been proposed in the literature to construct orthogonal moment invariants of general multi-channel functions. Given a specific type of multi-channel data, we demonstrate how to utilize the new method to derive all possible invariants and eliminate dependences among them. We obtain independent sets of invariants with low orders and low degrees for RGB images, 2D vector fields and color volume data. Based on synthetic and real multi-channel data, we conduct extensive experiments to evaluate the stability and discriminability of these invariants and their robustness to noise. The results show that new moment invariants significantly outperform previous moment invariants of multi-channel data in RGB image classification and vortex detection in 2D vector fields.

arXiv:2111.08513

Comparing Cross Correlation-Based Similarities

The real-valued Jaccard and coincidence indices, in addition to their conceptual and computational simplicity, have been verified to be able to provide promising results in tasks such as template matching, tending to yield peaks that are sharper and narrower than those typically obtained by standard cross-correlation, while also attenuating substantially secondary matchings. In this work, the multiset-based correlations based on the real-valued multiset Jaccard and coincidence indices are compared from the perspective of template matching, with encouraging results which have implications for pattern recognition, deep learning, and scientific modeling in general. The multiset-based correlation methods, and especially the coincidence index, presented remarkable performance characterized by sharper and narrower peaks while secondary peaks were attenuated, which was maintained even in presence of intense levels of noise. In particular, the two methods derived from the coincidence index led to particularly interesting results. The cross correlation, however, presented the best robustness to symmetric additive noise, which suggested a new combination of the considered approaches. After a preliminary investigation of the relative performance of the multiset approaches, as well as the classic cross-correlation, a systematic comparison framework is proposed and applied for the study of the aforementioned methods. Several results are reported, including the confirmation, at least for the considered type of data, of the coincidence correlation as providing enhanced performance regarding detection of narrow, sharp peaks while secondary matches are duly attenuated. The combined method also resulted promising for dealing with signals in presence of intense additive noise.

arXiv:2111.02783

Radio Sensing with Large Intelligent Surface for 6G

This paper leverages the potential of Large Intelligent Surface (LIS) for radio sensing in 6G wireless networks. Major research has been undergone about its communication capabilities but it can be exploited as a formidable tool for radio sensing. By taking advantage of arbitrary communication signals occurring in the scenario, we apply direct processing to the output signal from the LIS to obtain a radio map that describes the physical presence of passive devices (scatterers, humans) which act as virtual sources due to the communication signal reflections. We then assess the usage of machine learning (k-means clustering), image processing and computer vision (template matching and component labeling) to extract meaningful information from these radio maps. As an exemplary use case, we evaluate this method for both active and passive user detection in an indoor setting. The results show that the presented method has high application potential as we are able to detect around 98% of humans passively and 100% active users by just using communication signals of commodity devices even in quite unfavorable Signal-to-Noise Ratio (SNR) conditions.

arXiv:2109.12327

Toward Personalized Medicine in Connectomic Deep Brain Stimulation

At the group-level, deep brain stimulation leads to significant therapeutic benefit in a multitude of neurological and neuropsychiatric disorders. At the single-patient level, however, symptoms may sometimes persist despite "optimal" electrode placement at established treatment coordinates. This may be partly explained by limitations of disease-centric strategies that are unable to account for heterogeneous phenotypes and comorbidities observed in clinical practice. Instead, tailoring electrode placement and programming to individual patients' symptom profiles may increase the fraction of top responding patients. Here, we propose a three-step, circuit-based framework that aims to develop patient-specific treatment targets that address the unique symptom constellation prevalent in each patient. First, we describe how a symptom network target library could be established by mapping beneficial or undesirable DBS effects to distinct circuits based on (retrospective) group-level data. Second, we suggest ways of matching the resulting symptom networks to circuits defined in the individual patient (template matching). Third, we introduce network blending as a strategy to calculate optimal stimulation targets and parameters by selecting and weighting a set of symptom-specific networks based on the symptom profile and subjective priorities of the individual patient. We integrate the approach with published literature and conclude by discussing limitations and future challenges.

arXiv:2109.06452공식 코드 · Papers with Code

Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments

Spiking neural networks (SNNs) offer both compelling potential advantages, including energy efficiency and low latencies and challenges including the non-differentiable nature of event spikes. Much of the initial research in this area has converted deep neural networks to equivalent SNNs, but this conversion approach potentially negates some of the advantages of SNN-based approaches developed from scratch. One promising area for high-performance SNNs is template matching and image recognition. This research introduces the first high-performance SNN for the Visual Place Recognition (VPR) task: given a query image, the SNN has to find the closest match out of a list of reference images. At the core of this new system is a novel assignment scheme that implements a form of ambiguity-informed salience, by up-weighting single-place-encoding neurons and down-weighting "ambiguous" neurons that respond to multiple different reference places. In a range of experiments on the challenging Nordland, Oxford RobotCar, SPEDTest, Synthia, and St Lucia datasets, we show that our SNN achieves comparable VPR performance to state-of-the-art and classical techniques, and degrades gracefully in performance with an increasing number of reference places. Our results provide a significant milestone towards SNNs that can provide robust, energy-efficient, and low latency robot localization.

arXiv:2109.04134

Tiny CNN for feature point description for document analysis: approach and dataset

In this paper, we study the problem of feature points description in the context of document analysis and template matching. Our study shows that the specific training data is required for the task especially if we are to train a lightweight neural network that will be usable on devices with limited computational resources. In this paper, we construct and provide a dataset with a method of training patches retrieval. We prove the effectiveness of this data by training a lightweight neural network and show how it performs in both documents and general patches matching. The training was done on the provided dataset in comparison with HPatches training dataset and for the testing we use HPatches testing framework and two publicly available datasets with various documents pictured on complex backgrounds: MIDV-500 and MIDV-2019.

arXiv:2109.00630

A Novel Multi-Centroid Template Matching Algorithm and Its Application to Cough Detection

Cough is a major symptom of respiratory-related diseases. There exists a tremendous amount of work in detecting coughs from audio but there has been no effort to identify coughs from solely inertial measurement unit (IMU). Coughing causes motion across the whole body and especially on the neck and head. Therefore, head motion data during coughing captured by a head-worn IMU sensor could be leveraged to detect coughs using a template matching algorithm. In time series template matching problems, K-Nearest Neighbors (KNN) combined with elastic distance measurement (esp. Dynamic Time Warping (DTW)) achieves outstanding performance. However, it is often regarded as prohibitively time-consuming. Nearest Centroid Classifier is thereafter proposed. But the accuracy is comprised of only one centroid obtained for each class. Centroid-based Classifier performs clustering and averaging for each cluster, but requires manually setting the number of clusters. We propose a novel self-tuning multi-centroid template-matching algorithm, which can automatically adjust the number of clusters to balance accuracy and inference time. Through experiments conducted on synthetic datasets and a real-world earbud-based cough dataset, we demonstrate the superiority of our proposed algorithm and present the result of cough detection with a single accelerometer sensor on the earbuds platform.

arXiv:2108.06009

SAR image matching algorithm based on multi-class features

Synthetic aperture radar has the ability to work 24/7 and 24/7, and has high application value. Propose a new SAR image matching algorithm based on multi class features, mainly using two different types of features: straight lines and regions to enhance the robustness of the matching algorithm; On the basis of using prior knowledge of images, combined with LSD (Line Segment Detector) line detection and template matching algorithm, by analyzing the attribute correlation between line and surface features in SAR images, selecting line and region features in SAR images to match the images, the matching accuracy between SAR images and visible light images is improved, and the probability of matching errors is reduced. The experimental results have verified that this algorithm can obtain high-precision matching results, achieve precise target positioning, and has good robustness to changes in perspective and lighting. The results are accurate and false positives are controllable.