Local Deep Features Research Articles

Robust Hashing with Deep Features and Meixner Moments for Image Copy Detection

Copy detection is a key task of image copyright protection. Most robust hashing schemes do not make satisfied performance of image copy detection yet. To address this, a robust hashing scheme with deep features and Meixner moments is proposed for image copy detection. In the proposed hashing, global deep features are extracted by applying tensor Singular Value Decomposition (t-SVD) to the three-order tensor constructed in the DWT domain of the feature maps calculated by the pre-trained VGG16. Since the feature maps in the DWT domain are slightly disturbed by digital operations, the constructed three-order tensor is stable and thus the desirable robustness is guaranteed. Moreover, since t-SVD can decompose a three-order tensor into multiple low-dimensional matrices reflecting intrinsic structure, the global deep feature calculation from the low-dimensional matrices can provide good discrimination. Local features are calculated by the block-based Meixner moments. As the Meixner moments are resistant to geometric transformation and can efficiently discriminate various images, the use of the block-based Meixner moments can make discriminative and robust local features. Hash is ultimately determined by quantifying and combining global deep features and local features. The results of extensive experiments on open image datasets demonstrate that the proposed robust hashing outperforms some state-of-the-art robust hashing schemes in terms of classification and copy detection performances.

Automatic identification of breech face impressions based on deep local features

Breech face impressions are an essential type of physical evidence in forensic investigations. However, their surface morphology is complex and varies based on the machining method used on the gun’s breech face, making traditional handcrafted local feature-based methods exhibit high false rates and are unsuitable for striated impressions. We proposed a deep local feature-based method for firearm identification utilizing Detector-Free Local Feature Matching with Transformers (LoFTR). This method removes the module of feature point detection and directly utilizes self and cross-attention layers in the Transformer to transform the convolved coarse-level feature maps into a series of dense feature descriptors. Subsequently, matches with high confidence scores are filtered based on the score matrix calculated from the dense descriptors. Finally, the screened initial matches are refined into the convolved fine-level features, and a correlation-based approach is used to obtain the exact location of the match. Validation tests were conducted using three authoritative sets of the breech face impressions datasets provided by the National Institute of Standards and Technology (NIST). The validation results show that, compared with the traditional handcrafted local-feature based methods, the proposed method in this paper yields a lower identification error rate. Notably, the method can not only deal with granular impressions, but can also be applied to the striated impressions. The results indicate that the method proposed in this paper can be utilized for comparative analysis of breech face impressions, and provide a new automatic identification method for forensic investigations.

Efficient Key Frame Extraction from Videos Using Convolutional Neural Networks and Clustering Techniques

One of the most reliable information sources is video, and in recent years, online and offline video consumption has increased to an unprecedented degree. One of the main difficulties in extracting information from videos is that unlike images, where information can be gleaned from a single frame, a viewer must watch the entire video in order to comprehend the context. In this work, we try to use various algorithmic techniques, such as deep neural networks and local features, in conjunction with a variety of clustering techniques, to find an efficient method of extracting interesting key frames from videos to summarize them. Video summarization plays a major role in video indexing, browsing, compression, analysis, and many other domains. One of the fundamental elements of video structure analysis is key frame extraction, which pulls significant frames out of the movie. An important frame from a video that may be used to summarize videos is called a key frame. We provide a technique that leverages convolutional neural networks in our suggested model, static video summarization, and key frame extraction from movies.

Species-Agnostic Patterned Animal Re-identification by Aggregating Deep Local Features

Access to large image volumes through camera traps and crowdsourcing provides novel possibilities for animal monitoring and conservation. It calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. Most existing re-identification methods rely on either hand-crafted local features or end-to-end learning of fur pattern similarity. The former does not need labeled training data, while the latter, although very data-hungry typically outperforms the former when enough training data is available. We propose a novel re-identification pipeline that combines the strengths of both approaches by utilizing modern learnable local features and feature aggregation. This creates representative pattern feature embeddings that provide high re-identification accuracy while allowing us to apply the method to small datasets by using pre-trained feature descriptors. We report a comprehensive comparison of different modern local features and demonstrate the advantages of the proposed pipeline on two very different species.

HALNet: Partial Point Cloud Registration Based on Hybrid Attention and Deep Local Features.

Point cloud registration is an important task in computer vision and robotics which is widely used in 3D reconstruction, target recognition, and other fields. At present, many registration methods based on deep learning have better registration accuracy in complete point cloud registration, but partial registration accuracy is poor. Therefore, a partial point cloud registration network, HALNet, is proposed. Firstly, a feature extraction network consisting mainly of adaptive graph convolution (AGConv), two-dimensional convolution, and convolution block attention (CBAM) is used to learn the features of the initial point cloud. Then the overlapping estimation is used to remove the non-overlapping points of the two point clouds, and the hybrid attention mechanism composed of self-attention and cross-attention is used to fuse the geometric information of the two point clouds. Finally, the rigid transformation is obtained by using the fully connected layer. Five methods with excellent registration performance were selected for comparison. Compared with SCANet, which has the best registration performance among the five methods, the RMSE(R) and MAE(R) of HALNet are reduced by 10.67% and 12.05%. In addition, the results of the ablation experiment verify that the hybrid attention mechanism and fully connected layer are conducive to improving registration performance.

SADGFeat: Learning local features with layer spatial attention and domain generalization

Local feature plays a pivotal role in various robotic tasks, including 3D reconstruction and visual localization. Although deep learning-based local features have proven superior to their traditional counterparts, they still face challenges in practical applications due to matching failures. These challenges primarily stem from inaccuracies in keypoint localization and the limited robustness of descriptors particularly with significant appearance changes. In this study, we introduce a novel method for local feature learning based on layer spatial attention and domain generalization. Firstly, a keypoint extraction strategy driven by layer spatial attention from high-level feature is proposed to enhance the accuracy of keypoint localization, progressing from coarse to fine granularity. Secondly, a new learning paradigm based on domain generalization is developed to extract local features with resilience against variations in illumination. To enrich the domain diversity within the training dataset, a real-time and lossless Fourier transform-based domain augmentation method is introduced. This method seamlessly integrates into the training process, enhancing the model's adaptability to varying domains. Additionally, explicit feature alignment-based representation learning is performed, further reinforcing the extraction of domain-invariant local features. Experimental results on public datasets demonstrate that the proposed method achieves state-of-the-art performance across various downstream tasks reliant on local feature matching, such as image matching, 3D reconstruction, and long-term visual localization.

Study on vibration signals identification method for pipeline leakage detection based on deep learning technology

For natural gas pipeline leakage systems based on distributed feedback fiber laser vibration sensors (DFB-FL), a novel neural network model (mCNN-LFLBs) integrating multi-scale convolutional neural networks (mCNN) with local feature extraction blocks (LFLBs) is proposed in this study. To address the problem of feature loss in the traditional signal image transfer process, the one-dimensional original signal is directly used as the input of the model, effectively maintaining the time-domain correlation of the leaked signal. The time-domain correlation of the leakage signal is preserved. To address the problem that traditional pattern recognition algorithms have a weak ability to extract deep features and local features, mCNN is established by this model, which realizes the use of convolution kernels of different scales to extract features of different frequency bands in one-dimensional signals. Additionally, LFLBs are introduced, which enhances the local expression ability of the model, further improves the feature mining quality of the model, and better presents the deep features of leaked signals. Experimental results demonstrate that the mCNN-LFLBs model has a classification accuracy of up to 98.6%, with a testing response time of approximately 10 ms, and outstanding performance in terms of convergence speed. These results highlight the potential practical application of the mCNN-LFLBs model in natural gas leak detection.

Hierarchical multihead self-attention for time-series-based fault diagnosis

Fault diagnosis is important for maintaining the safety and effectiveness of chemical process. Considering the multivariate, nonlinear, and dynamic characteristic of chemical process, many time-series-based data-driven fault diagnosis methods have been developed in recent years. However, the existing methods have the problem of long-term dependency and is difficult to train due to the sequential way of training. To overcome these problems, a novel fault diagnosis method based on time-series and the hierarchical multi-head self-attention (HMSAN) is proposed for chemical process. First, a sliding window strategy is adopted to construct the normalized time-series dataset. Second, the HMSAN is developed to extract the time-relevant features from the time-series process data. It improves the basic self-attention model in both width and depth. With the multi-head structure, the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features. However, the multiple heads in parallel lead to redundant information, which cannot improve the diagnosis performance. With the hierarchical structure, the redundant information is reduced and the deep local time-related features are further extracted. Besides, a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency. Finally, the effectiveness of the proposed method is demonstrated by two chemical cases. The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-art approaches.

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

Few-shot fine-grained image classification (FSFGIC) methods refer to the classification of images (e.g., birds, flowers, and airplanes) belonging to different subclasses of the same species by a small number of labeled samples. Through feature representation learning, FSFGIC methods can make better use of limited sample information, learn more discriminative feature representations, greatly improve the classification accuracy and generalization ability, and thus achieve better results in FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local and/or global deep feature representation learning, class representation learning, and task-specific feature representation learning). In addition, the existing popular datasets, current challenges and future development trends of feature representation learning on FSFGIC are also described.

Channel Semantic Enhancement-Based Emotional Recognition Method Using SCLE-2D-CNN

The existing EEG emotion classification methods have some problems, such as insufficient emotion representation and lack of targeted channel enhancement module due to feature redundancy. To this end, a novel EEG emotion recognition method (SCLE-2D-CNN) combining scaled convolutional layer (SCLs), enhanced channel module and two-dimensional convolutional neural network (2D-CNN) is proposed. Firstly, the time-frequency features of multi-channel EEG emotional signals were extracted by stacking scl layer by layer. Secondly, channel enhancement module is used to reassign different importance to all EEG physical channels. Finally, 2D-CNN was used to obtain deep local spatiotemporal features and complete emotion classification. The experimental results show that the accuracy of SEED data set and F1 are 98.09% and 97.00%, respectively, and the binary classification accuracy of DEAP data set is 98.06% and 96.83%, respectively, which are superior to other comparison methods. The proposed method has a certain application prospect in the recognition of human mental state.

TECD_Attention: Texture-enhanced and cross-domain attention modeling for visual place recognition

Visual place recognition (VPR) is a challenging task for visual computing in the field of robot navigation. However, most of the existing methods fail to learn the most salient features of place images by simple CNN feature or popular Transformer feature due to the inconsistency problem commonly existing in VPR datasets, which limits the robustness and interpretability of the model. In addition, existing state-of-the-art methods only capture general features of original places with multi-scale CNN or transformer features and ignore texture characteristics existing in place images, resulting in suboptimal recognition performance. To cope with the above issues, we propose a novel visual place recognition network, named Texture-enhanced Cross-domain Attention Transformer (TECD_Attention). Specially, a cross-attention Transformer is first used for fusing deep attentive local and global features to improve the multi-scale feature representation of the recognition model. Second, a texture-enhanced cross-domain attention block is designed to construct the final feature descriptor by fusing texture features and attentive local–global features. Then, a tripled loss function is used for matching top-ranked reference places from the place database to a query place. Last, effective and efficient place re-ranking is achieved by training an adapted weakly supervised re-ranking network relying on the similarity computing between the query place and the top-ranked places. Our approach is carried out in extensive experiments on four challenging datasets. Our model has achieved 96.2%, 94.6%, 95.9%, and 96.8% average recall based on top 1% Candidate scenario on Tokyo 24/7, Pitts250k, VPRiCE, and SUN397 datasets, respectively. Therefore, Compared with the existing state-of-the-art VPR methods, TECD_Attention performs superior on robot place recognition in challenging environments. Hence, we can conclude that this is a robust model for robot visual place recognition in challenging environments.

Efficient Retrieval of Images with Irregular Patterns Using Morphological Image Analysis: Applications to Industrial and Healthcare Datasets.

Image retrieval is the process of searching and retrieving images from a datastore based on their visual content and features. Recently, much attention has been directed towards the retrieval of irregular patterns within industrial or healthcare images by extracting features from the images, such as deep features, colour-based features, shape-based features, and local features. This has applications across a spectrum of industries, including fault inspection, disease diagnosis, and maintenance prediction. This paper proposes an image retrieval framework to search for images containing similar irregular patterns by extracting a set of morphological features (DefChars) from images. The datasets employed in this paper contain wind turbine blade images with defects, chest computerised tomography scans with COVID-19 infections, heatsink images with defects, and lake ice images. The proposed framework was evaluated with different feature extraction methods (DefChars, resized raw image, local binary pattern, and scale-invariant feature transforms) and distance metrics to determine the most efficient parameters in terms of retrieval performance across datasets. The retrieval results show that the proposed framework using the DefChars and the Manhattan distance metric achieves a mean average precision of 80% and a low standard deviation of ±0.09 across classes of irregular patterns, outperforming alternative feature-metric combinations across all datasets. Our proposed ImR framework performed better (by 8.71%) than Super Global, a state-of-the-art deep-learning-based image retrieval approach across all datasets.

Semisupervised Deep Features of Time-Frequency Maps for Multimodal Emotion Recognition

Traditional approaches for emotion recognition utilize unimodal physiological signals. The effectiveness of such systems is affected by some limitations. To overcome them, this paper proposes a new method based on time-frequency maps that extract the features from multimodal biological signals. At first, the fusion of electroencephalogram (EEG) and peripheral physiological signal (PPS) is performed, and then, the two-dimensional discrete orthonormal Stockwell transform (2D-DOST) of the multimodal signal matrix is calculated to obtain time-frequency maps. A convolutional neural network (CNN) is then utilized to extract the local deep features from the absolute output of the 2D-DOST. Since there are uninformative deep features, the semisupervised dimension reduction scheme reduces them by balancing the generalization and discrimination. Finally, the classifier recognizes the emotion. The Bayesian optimizer finds the proper SSDR and classifier parameter values to maximize the recognition accuracy. The performance of the proposed method is evaluated on the DEAP dataset considering the two- and four-class scenarios through extensive simulations. This dataset consists of electroencephalograph (EEG) signals in 32 channels and peripheral physiological signals (PPSs) in eight channels from 32 subjects. The proposed method reaches the accuracy of 0.953 and 0.928 for two- and four-class scenarios, respectively. The results indicate the efficiency of the multimodal signals for detecting emotions compared to that of unimodal signals. Also, the results indicate that the proposed method outperforms the recently introduced ones.

Deep feature interactive network for machinery fault diagnosis using multi-source heterogeneous data

Infrared thermal images have been applied for monitoring health condition of machines due to the noncontact and nonintrusive manner. While fault diagnosis performance of those deep neural networks (DNNs) that use infrared thermal images is restricted by the information learned from single sensor. In this study, multi-source heterogeneous data (i.e., infrared thermal images and vibration signals) are used for machinery fault diagnosis. A new DNN, i.e., deep feature interactive network (DFINet) is proposed for machinery fault diagnosis, where a novel interactive feature extraction module is developed for adaptive feature fusion on multi-source heterogeneous data. Firstly, the private and public features of multi-source heterogeneous data are extracted separately by measuring the distribution discrepancy between heterogeneous features in the feature interactive module. The feature splicing is implemented to interactively fuse common fault features of heterogeneous data and to preserve private unique features. A global feature fusion module is further proposed for adaptive fusion of superficial local features and deep abstract features learned by different feature interactive modules. The experimental results on a rotor test-bed and gearbox test-bed indicate that DFINet is promising for fusion and feature extraction on multi-source heterogeneous data in machinery fault diagnosis.

A deep learning-based local feature extraction method for improved image matching and surface reconstruction from Yutu-2 PCAM images on the Moon

Topographic reconstruction of the lunar surface or other planets is important to engineering applications and scientific research in a planetary exploration mission. The typical methods of terrain reconstruction are usually based on photogrammetry techniques. Structure-from-Motion (SfM) is one of the most effective and commonly used photogrammetric technologies that estimate three-dimensional structures from two-dimensional image sequences. To find correspondences and align photos, SfM approaches require invariant features, such as Scale Invariant Feature Transform (SIFT). The hand-crafted features, however, seriously degrade performance due to weak texture and low light conditions causing image matching failure, which will directly affect the accuracy and robustness of reconstruction. Robust local descriptors based on deep learning outperform hand-crafted descriptors since convolutional neural networks are more robust than hand-engineered representations. Therefore, a novel and robust deep learning-based local feature extraction method is proposed, comprising two branch networks integrated with attention mechanisms for generating reliable keypoints and descriptors, respectively. Furthermore, a 3D terrain surface reconstruction workflow is constructed by combining it with the modern advanced image matching method and SfM system. The effectiveness of the proposed method and the workflow were verified in experiments using Panoramic Camera (PCAM) images acquired from three waypoints explored by the Yutu-2 lunar rover during the Chang’e-4 mission. We also illustrate how our approach supports other applications, such as creating panoramic mosaics of surface imagery. This provides a new and powerful method for planetary terrain reconstruction at a high spatial resolution that can meet the requirements for rover navigation and positioning, as well as geological analysis of the Moon and other planets. The source codes developed in this study are openly available at https://github.com/Atypical-Programmer/Deep_Reconstruction_Workflow.

Novel dual-network autoencoder based adversarial domain adaptation with Wasserstein divergence for fault diagnosis of unlabeled data

Intelligent fault diagnostic techniques based on deep learning have been developed by leaps and bounds, but it is quite difficult to construct a good fault diagnosis model without obtaining sufficient fault data labels. To solve this problem, this article proposes a novel dual-network autoencoder based adversarial domain adaptation with Wasserstein divergence (DWADA). Firstly, a dual-network autoencoder composed of the convolutional neural network (CNN) and the long short-term memory (LSTM) is regarded as a feature extractor for extracting local deep features and adding temporal feature information, while unsupervised reconstruction of the source domain data can ensure high accuracy of the classifier. Secondly, the domain discriminator forms an adversarial training with the feature extractor to facilitate the feature extractor to extract domain-invariant features for classification by minimizing the Wasserstein distance that measures the difference in feature distribution between different domains. Finally, Wasserstein divergence is introduced to the adversarial process to remove the k-Lipschitz constraint for improving the stability of the training. The Tennessee Eastman process (TEP) and the industrial three-phase flow process (TPFP) are applied to verify the performance of DWADA. Simulation results show that DWADA outperforms other related methods in transfer fault diagnosis tasks under different operating conditions.

FedFTN: Personalized federated learning with deep feature transformation network for multi-institutional low-count PET denoising

Low-count PET is an efficient way to reduce radiation exposure and acquisition time, but the reconstructed images often suffer from low signal-to-noise ratio (SNR), thus affecting diagnosis and other downstream tasks. Recent advances in deep learning have shown great potential in improving low-count PET image quality, but acquiring a large, centralized, and diverse dataset from multiple institutions for training a robust model is difficult due to privacy and security concerns of patient data. Moreover, low-count PET data at different institutions may have different data distribution, thus requiring personalized models. While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, addressing the large domain shift in the application of multi-institutional low-count PET denoising remains a challenge and is still highly under-explored. In this work, we propose FedFTN, a personalized federated learning strategy that addresses these challenges. FedFTN uses a local deep feature transformation network (FTN) to modulate the feature outputs of a globally shared denoising network, enabling personalized low-count PET denoising for each institution. During the federated learning process, only the denoising network’s weights are communicated and aggregated, while the FTN remains at the local institutions for feature transformation. We evaluated our method using a large-scale dataset of multi-institutional low-count PET imaging data from three medical centers located across three continents, and showed that FedFTN provides high-quality low-count PET images, outperforming previous baseline FL reconstruction methods across all low-count levels at all three institutions.

Partial Point Cloud Registration With Deep Local Feature

How to accurately register partial point cloud still remains a challenging task, because of its irregular and unordered structure in a non-Euclidean space, noise, outliers, and other unfavorable factors. In this paper, an effective partial point cloud registration network is proposed, by devising a two-stage deep local feature extraction process and an outlier filtering strategy. To be specific, on the one hand, to effectively capture geometric interdependency in low-level space, a local attention feature extraction module is explored to extract local contextual attention features, by highlighting different attention weights on neighborhoods. On the other hand, in local feature aggregation module, two position encoding blocks are applied to increase the receptive field of each point in high-level space. Of these, an attentive pooling can automatically learn important local features to alleviate the possible information loss. Furthermore, to derive the weight of the putative correspondence, an outlier filtering module is designed by consisting of point context normalization block, differentiable pooling and differentiable unpooling layer. Moreover, in order to enhance robustness, a weighting point cloud registration model is formulated to alleviate outliers, by considering the contribution of each correspondence. Experiments on multiple datasets demonstrate that the proposed approach is competitive to several state-of-the-art algorithms. Code is publicly available at <uri>https://github.com/zhlSunLab/DLF</uri>.

HGECDA: A Heterogeneous Graph Embedding Model for CircRNA-Disease Association Prediction.

Circular RNAs (circRNAs) are specifically and abnormally expressed in disease tissues, and thus can be used as biomarkers to diagnose relevant diseases. Predicting circRNA-disease associations will provide essential clues to reveal molecular mechanisms of disease development and discover novel therapeutic targets. Existing algorithms ignore the heterogeneous biological association information related to microRNAs (miRNAs). Based on a heterogeneous graph embedding model, a novel circRNA-disease association prediction method called HGECDA is developed in this paper. The heterogeneous graph network containing circRNA-miRNA-disease association information is first constructed. To sample the heterogeneous information, the meta-path-based random walk that can capture the relevance between various types of nodes is employed. Then, the path embedding model based on skip-gram and random negative sampling is built to acquire the initial feature vectors of circRNAs and diseases. Finally, the CosMulformer model with linearized self-attention and Hadamard product is designed to obtain the circRNA-disease interaction vectors and conduct the prediction task. Experimental results demonstrate the critical role of miRNA in enriching the information of the feature space, the effectiveness of the CosMulformer model in picking out deep local interaction features, and the feasibility of the Hadamard product chosen as the integration pattern in the CosMulformer model. Compared with existing state-of-the-art methods on the same dataset, HGECDA performs better than the other seven algorithms. Moreover, the case studies about breast cancer and colorectal cancer demonstrate the practical value of HGECDA in predicting potential circRNA-disease associations.

DeepMatcher: A deep transformer-based network for robust and accurate local feature matching

Local feature matching constitutes the cornerstone of multiple computer vision applications (e.g., 3D reconstruction and long-term visual localization), and has been successfully resolved by detector-free methods. To further improve the matching performance, more recent research has focused on designing sophisticated architectures but endures additional computational overhead. In this study, with a different perspective from previous studies, we aim to develop a deep and compact matching network to improve performance while reducing computing cost. The key insight is that a local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features. To this end, we propose DeepMatcher, a deep transformer-based network that tackles the inherent obstacles of not being able to build a deep local feature matcher with current methods. DeepMatcher consists of: (1) a local feature extractor (LFE), (2) a feature-transition module (FTM), (3) a slimming transformer (SlimFormer), (4) a coarse matches module (CMM), and (5) a fine matches module (FMM). The LFE is utilized to generate dense keypoints with enriched features from the images. We then introduce the FTM to ensure a smooth transition of feature scopes from LFE to the subsequent SlimFormer because of their different receptive fields. Subsequently, we develop SlimFormer dedicated to DeepMatcher, which leverages vector-based attention to model the relevance among all keypoints, enabling the network to construct a deep Transformer architecture with less computational cost. Relative position encoding is applied to each SlimFormer to explicitly disclose the relative distance information, thereby improving the representation of the keypoints. A layer-scale strategy is also employed in each SlimFormer to enable the network to adaptively assimilate message exchange, thus endowing it to simulate human behavior, in which humans can acquire different matching cues each time they scan an image pair. By interleaving the self- and cross-SlimFormers multiple times, DeepMatcher can easily establish pixel-wise dense matches at the coarse level using the CMM. Finally, we consider match refinement as a combination of classification and regression problems and design an FMM to predict confidence and offset concurrently, thus generating robust and accurate matches. Compared with our baseline LoFTR in indoor/outdoor pose estimation, DeepMatcher surpasses it by 3.32%/2.91% in AUC@5∘. Besides, DeepMatcher and DeepMatcher-L significantly reduce computational cost and only consume 77.89% and 92.46% GFLOPs of LoFTR. Large DeepMatcher considerably outperforms state-of-the-art methods on several benchmarks, including outdoor pose estimation (MegaDepth dataset), indoor pose estimation (ScanNet dataset), homography estimation (HPatches dataset), and image matching (HPatches dataset), demonstrating the superior matching capability of a deep local feature matcher.