Reusable Architecture Growth for Continual Stereo Matching.

The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of heterogeneous scenes at deployment time. However, training samples are typically acquired continuously in practical applications, making the capability to learn new scenes continually even more crucial. For this purpose, we propose to perform continual stereo matching where a model is tasked to 1) continually learn new scenes, 2) overcome forgetting previously learned scenes, and 3) continuously predict disparities at inference. We achieve this goal by introducing a Reusable Architecture Growth (RAG) framework. RAG leverages task-specific neural unit search and architecture growth to learn new scenes continually in both supervised and self-supervised manners. It can maintain high reusability during growth by reusing previous units while obtaining good performance. Additionally, we present a Scene Router module to adaptively select the scene-specific architecture path at inference. Comprehensive experiments on numerous datasets show that our framework performs impressively in various weather, road, and city circumstances and surpasses the state-of-the-art methods in more challenging cross-dataset settings. Further experiments also demonstrate the adaptability of our method to unseen scenes, which can facilitate end-to-end stereo architecture learning and practical deployment.

Polyphyllin VII alleviates pulmonary hypertension by inducing miR-205-5p to target the ß-catenin pathway.

OBJECTIVE: This study aims to investigate the impact of Polyphyllin VII (PP7) on pulmonary hypertension (PH) and elucidate the underlying mechanism involving microRNA (miR)-205-5p/ß-catenin. METHODS: The PH rat model was induced through hypoxia exposure. The effects of intraperitoneal injection of PP7 on pulmonary artery tissue pathology, hemodynamics, miR-205-5p expression and ß-catenin protein levels were assessed. In vitro, pulmonary arterial smooth muscle cells (PASMCs) were subjected to hypoxic conditions. Moreover, miR-205-5p and/or ß-catenin were overexpressed through transfection. PASMCs were pre-cultured in 20 µM PP7, and subsequent measurements included proliferation, apoptosis and vascular remodeling protein expression. RESULTS: PP7 ameliorated PH symptoms in rats, upregulated miR-205-5p expression and inhibited ß-catenin protein expression. Furthermore, miR-205-5p upregulation inhibited ß-catenin expression in PASMCs. The overexpression of ß-catenin aggravated hypoxia-induced proliferation, inhibited apoptosis and further augmented VEGF and α-SMA protein expression. Additionally, miR-205-5p overexpression alleviated the hypoxia-induced PASMC proliferation and apoptosis by inhibiting ß-catenin protein expression. Under hypoxic conditions, PP7 significantly elevated miR-205-5p while downregulating ß-catenin protein expression. Furthermore, inhibiting miR-205-5p counteracted the inhibitory effect of PP7 on ß-catenin, consequently blocking the regulatory role of PP7 in PASMC proliferation and apoptosis. CONCLUSION: PP7 likely modulates ß-catenin protein levels by promoting miR-205-5p expression, thereby alleviating PH, vascular remodeling and airway smooth muscle remodeling.

Outcomes of Holmium Laser, Cryoablation, and Budesonide Inhalation for Treating Severe Central Airway Stenosis in Infants.

BACKGROUND: Central airway stenosis (CAS) in infants is characterized by dysphonia, dyspnea, cyanosis, repeated apnea, and infection. This case series study aimed to evaluate the safety and efficacy of holmium laser, cryoablation and budesonide inhalation in treating infants with severe CAS. METHODS: This retrospective study reviewed medical records data of 28 infants with severe CAS who underwent holmium laser treatment with cryoablation and/or balloon dilatation and budesonide inhalation therapy at Shanghai Children's Medical Center between June 2014 and May 2020. Outcomes were defined as treatment success when the stenotic area was <25% for the normal age group with stable reopening diameter at one-year follow-up. RESULTS: Patients' mean age was 12.8 ± 8.8 months and 17 (60%) were male. Sixteen cases had web-like stenosis and 12 had scar contracture stenosis. Among 16 patients with web-like stenosis, 8 (50%) underwent balloon dilation with cryotherapy and 8 (50%) underwent balloon dilation only; treatment success was achieved in 10 (62.5%) cases and after revised treatments in 5 (31.25%) cases. Among 12 patients with scar contracture stenosis, 6 (50%) underwent balloon dilation with cryotherapy, 4 (33.3%) underwent cryotherapy and 2 (16.7%) underwent balloon dilation only; treatment success was achieved in 3 (23.1%) cases and after 1-4 revised treatments in 8 (61.5%) cases. Symptoms of the 2 unsuccessful (7.1%) cases were relieved after tracheal stent insertion. Neither severe adverse events nor complications were observed during follow-up. CONCLUSION: Holmium laser with cryoablation followed by budesonide inhalation therapy safely and effectively cleans stenotic tissues and maintains airway reopening. Balloon dilation after holmium laser is recommended for treating web-like stenosis.

Graph convolutional network with tree-guided anisotropic message passing.

Graph Convolutional Networks (GCNs) with naive message passing mechanisms have limited performance due to the isotropic aggregation strategy. To remedy this drawback, some recent works focus on how to design anisotropic aggregation strategies with tricks on feature mapping or structure mining. However, these models still suffer from the low ability of expressiveness and long-range modeling for the needs of high performance in practice. To this end, this paper proposes a tree-guided anisotropic GCN, which applies an anisotropic aggregation strategy with competitive expressiveness and a large receptive field. Specifically, the anisotropic aggregation is decoupled into two stages. The first stage is to establish the path of the message passing on a tree-like hypergraph consisting of substructures. The second one is to aggregate the messages with constrained intensities by employing an effective gating mechanism. In addition, a novel anisotropic readout mechanism is constructed to generate representative and discriminative graph-level features for downstream tasks. Our model outperforms baseline methods and recent works on several synthetic benchmarks and datasets from different real-world tasks. In addition, extensive ablation studies and theoretical analyses indicate the effectiveness of our proposed method.

Nasal nitric oxide in healthy Chinese children aged 6-18 years.

Objectives: To obtain the normal values of fractional concentration of nasal nitric oxide in Chinese children aged 6-18 years, so as to provide reference for clinical diagnosis. Methods: 2,580 out of 3,200 children (1,359 males and 1,221 females), whom were included from 12 centers around China were taken tests, their height and weight were also recorded. Data were used to analyze the normal range and influencing factors of fractional concentration of nasal nitric oxide values. Measurements: Data was measured using the Nano Coulomb Breath Analyzer (Sunvou-CA2122, Wuxi, China), according to the American Thoracic Society/European Respiratory Society (ATS/ERS) recommendations. Main Results: We calculated the normal range and prediction equation of fractional concentration of nasal nitric oxide values in Chinese children aged 6-18 years. The mean FnNO values of Chinese aged 6-18 yrs was 454.5 ± 176.2 ppb, and 95% of them were in the range of 134.5-844.0 ppb. The prediction rule of FnNO values for Chinese children aged 6-11 yrs was: FnNO = 298.881 + 17.974 × age. And for children aged 12-18 yrs was: FnNO = 579.222-30.332 × (male = 0, female = 1)-5.503 × age. Conclusions: Sex and age were two significant predictors of FnNO values for Chinese children(aged 12-18 yrs). Hopefully this study can provide some reference value for clinical diagnosis in children.

Comparison of Pulmonary Function and Inflammation in Children/Adolescents with New-Onset Asthma with Different Adiposity Statuses.

(1) Background: The relationship between obesity and asthma is still uncertain. This study aimed to investigate the effect of overweight/obesity on the pulmonary function of patients with new-onset pediatric asthma and explore the possible causative factors related to concomitant obesity and asthma. (2) Methods: Patients aged 5 to 17 years old with newly diagnosed mild to moderate asthma were recruited from June 2018 to May 2019, from a respiratory clinic in Shanghai, China. Participants were categorized into three groups: normal weight, overweight, and obese asthma. A family history of atopy and patients' personal allergic diseases were recorded. Pulmonary function, fractional exhaled nitric oxide (FeNO), eosinophils, serum-specific immunoglobulins E (sIgE), serum total IgE (tIgE), and serum inflammatory biomarkers (adiponectin, leptin, Type 1 helper T, and Type 2 helper T cytokines) were tested in all participants. (3) Results: A total of 407 asthma patients (197 normal weight, 92 overweight, and 118 obese) were enrolled. There was a reduction in forced expiratory volume in the first second (FEV1)/forced vital capacity (FVC), FEV1/FVC%, and FEF25-75% in the overweight/obese groups. No difference was found between the study groups in the main allergy characteristics. Leptin levels were higher while adiponectin was lower in asthmatics with obesity. Higher levels of IL-16 were found in overweight/obese asthmatic individuals than in normal-weight individuals. (4) Conclusions: Obesity may have an effect on impaired pulmonary function. While atopic inflammation plays an important role in the onset of asthma, nonatopic inflammation (including leptin and adiponectin) increases the severity of asthma in overweight/obese patients. The significance of different levels of IL-16 between groups needs to be further studied.

Subgraph-aware graph structure revision for spatial-temporal graph modeling.

Spatial-temporal graph modeling has been widely studied in many fields, such as traffic forecasting and energy analysis, where data has time and space properties. Existing methods focus on capturing stable and dynamic spatial correlations by constructing physical and virtual graphs along with graph convolution and temporal modeling. However, existing methods tending to smooth node features may obscure the spatial-temporal patterns among nodes. Worse, the graph structure is not always available in some fields, while the manually constructed stable or dynamic graphs cannot necessarily reflect the true spatial correlations either. This paper proposes a Subgraph-Aware Graph Structure Revision network (SAGSR) to overcome these limitations. Architecturally, a subgraph-aware structure revision graph convolution module (SASR-GCM) is designed, which revises the learned stable graph to obtain a dynamic one to automatically infer the dynamics of spatial correlations. Each of these two graphs is separated into one homophilic subgraph and one heterophilic subgraph by a subgraph-aware graph convolution mechanism, which aggregates similar nodes in the homophilic subgraph with positive weights, while keeping nodes with dissimilar features in the heterophilic subgraph mutually away with negative aggregation weights to avoid pattern obfuscation. By combining a gated multi-scale temporal convolution module (GMS-TCM) for temporal modeling, SAGSR can efficiently capture the spatial-temporal correlations and extract complex spatial-temporal graph features. Extensive experiments, conducted on two specific tasks: traffic flow forecasting and energy consumption forecasting, indicate the effectiveness and superiority of our proposed approach over several competitive baselines.

You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization.

Recently neural architecture search (NAS) has raised great interest in both academia and industry. However, it remains challenging because of its huge and non-continuous search space. Instead of applying evolutionary algorithm or reinforcement learning as previous works, this paper proposes a direct sparse optimization NAS (DSO-NAS) method. The motivation behind DSO-NAS is to address the task in the view of model pruning. To achieve this goal, we start from a completely connected block, and then introduce scaling factors to scale the information flow between operations. Next, sparse regularizations are imposed to prune useless connections in the architecture. Lastly, an efficient and theoretically sound optimization method is derived to solve it. Our method enjoys both advantages of differentiability and efficiency, therefore it can be directly applied to large datasets like ImageNet and tasks beyond classification. Particularly, on the CIFAR-10 dataset, DSO-NAS achieves an average test error 2.74 percent, while on the ImageNet dataset DSO-NAS achieves 25.4 percent test error under 600M FLOPs with 8 GPUs in 18 hours. As for semantic segmentation task, DSO-NAS also achieve competitive result compared with manually designed architectures on the PASCAL VOC dataset. Code is available at https://github.com/XinbangZhang/DSO-NAS.

DATA: Differentiable ArchiTecture Approximation With Distribution Guided Sampling.

Neural architecture search (NAS) is inherently subject to the gap of architectures during searching and validating. To bridge this gap effectively, we develop Differentiable ArchiTecture Approximation (DATA) with Ensemble Gumbel-Softmax (EGS) estimator and Architecture Distribution Constraint (ADC) to automatically approximate architectures during searching and validating in a differentiable manner. Technically, the EGS estimator consists of a group of Gumbel-Softmax estimators, which is capable of converting probability vectors to binary codes and passing gradients reversely, reducing the estimation bias in a differentiable way. To narrow the distribution gap between sampled architectures and supernet, further, the ADC is introduced to reduce the variance of sampling during searching. Benefiting from such modeling, architecture probabilities and network weights in the NAS model can be jointly optimized with the standard back-propagation, yielding an end-to-end learning mechanism for searching deep neural architectures in an extended search space. Conclusively, in the validating process, a high-performance architecture that approaches to the learned one during searching is readily built. Extensive experiments on various tasks including image classification, few-shot learning, unsupervised clustering, semantic segmentation and language modeling strongly demonstrate that DATA is capable of discovering high-performance architectures while guaranteeing the required efficiency. Code is available at https://github.com/XinbangZhang/DATA-NAS.

Extracting Effective Image Attributes with Refined Universal Detection.

Recently, image attributes containing high-level semantic information have been widely used in computer vision tasks, including visual recognition and image captioning. Existing attribute extraction methods map visual concepts to the probabilities of frequently-used words by directly using Convolutional Neural Networks (CNNs). Typically, two main problems exist in those methods. First, words of different parts of speech (POSs) are handled in the same way, but non-nominal words can hardly be mapped to visual regions through CNNs only. Second, synonymous nominal words are treated as independent and different words, in which similarities are ignored. In this paper, a novel Refined Universal Detection (RUDet) method is proposed to solve these two problems. Specifically, a Refinement (RF) module is designed to extract refined attributes of non-nominal words based on the attributes of nominal words and visual features. In addition, a Word Tree (WT) module is constructed to integrate synonymous nouns, which ensures that similar words hold similar and more accurate probabilities. Moreover, a Feature Enhancement (FE) module is adopted to enhance the ability to mine different visual concepts in different scales. Experiments conducted on the large-scale Microsoft (MS) COCO dataset illustrate the effectiveness of our proposed method.

An Interrater Reliability Study of Pulmonary Function Assessment With a Portable Spirometer.

BACKGROUND: In this study, we aimed to validate the agreement between pulmonary function measurements obtained with a portable spirometer and measurements obtained with conventional spirometry in Chinese pediatric and adult populations. METHODS: Pulmonary function testing was performed to evaluate subjects enrolled at Shanghai Zhongshan Hospital (n = 104) and Shanghai Children's Medical Center (n = 103). The portable spirometers and conventional devices were applied to each subject with a 20-min quiescent period between each measurement. Pulmonary function parameters of FVC, FEV1, peak expiratory flow, maximum expiratory flow at 25%, 50%, and 75% of FVC (MEF25, MEF50, and MEF75, respectively), and FEV1/FVC% were compared with intraclass correlation and Bland-Altman methods. RESULTS: A satisfactory concordance of pulmonary function was observed between spirometry measurements obtained with portable versus conventional spirometers. Intraclass correlation indicated excellent reliability (>0.75) for all pulmonary function indicators in pediatric and adult subjects. Significant positive correlations of all variables measured with different spirometers were observed (all P < .001). No significant bias was observed in either group, although limits of agreement varied. Funnel effects were observed for peak expiratory flow in pediatric subjects and for FVC, FEV1, MEF50, and MEF25 in adult subjects. CONCLUSIONS: The portable spirometer is an alternative to the conventional device for the measurement of pulmonary function. Compared with the conventional device, the portable spirometer is expected to provide convenient, operational, and financial advantages.

Baselines Extraction from Curved Document Images via Slope Fields Recovery.

Baselines estimation is a critical preprocessing step for many tasks of document image processing and analysis. The problem is very challenging due to arbitrarily complicated page layouts and various types of image quality degradations. This paper proposes a method based on slope fields recovery for curved baseline extraction from a distorted document image captured by a hand-held camera. Our method treats the curved baselines as the solution curves of an ordinary differential equation defined on a slope field. By assuming the page shape is a smooth and developable surface, we investigate a type of intrinsic geometric constraints of baselines to estimate the latent slope field. The curved baselines are finally obtained by solving an ordinary differential equation through the Euler method. Unlike the traditional text-lines based methods, our method is free from text-lines detection and segmentation. It can exploit multiple visual cues other than horizontal text-lines available in images for baselines extraction and is quite robust to document scripts, various types of image quality degradation (e.g., image distortion, blur and non-uniform illumination), large areas of non-textual objects and complex page layouts. Extensive experiments on synthetic and real-captured document images are implemented to evaluate the performance of the proposed method.

Deep Self-Evolution Clustering.

Clustering is a crucial but challenging task in pattern analysis and machine learning. Existing methods often ignore the combination between representation learning and clustering. To tackle this problem, we reconsider the clustering task from its definition to develop Deep Self-Evolution Clustering (DSEC) to jointly learn representations and cluster data. For this purpose, the clustering task is recast as a binary pairwise-classification problem to estimate whether pairwise patterns are similar. Specifically, similarities between pairwise patterns are defined by the dot product between indicator features which are generated by a deep neural network (DNN). To learn informative representations for clustering, clustering constraints are imposed on the indicator features to represent specific concepts with specific representations. Since the ground-truth similarities are unavailable in clustering, an alternating iterative algorithm called Self-Evolution Clustering Training (SECT) is presented to select similar and dissimilar pairwise patterns and to train the DNN alternately. Consequently, the indicator features tend to be one-hot vectors and the patterns can be clustered by locating the largest response of the learned indicator features. Extensive experiments strongly evidence that DSEC outperforms current models on twelve popular image, text and audio datasets consistently.

Local-Aggregation Graph Networks.

Convolutional neural networks (CNNs) provide a dramatically powerful class of models, but are subject to traditional convolution that can merely aggregate permutation-ordered and dimension-equal local inputs. It causes that CNNs are allowed to only manage signals on Euclidean or grid-like domains (e.g., images), not ones on non-Euclidean or graph domains (e.g., traffic networks). To eliminate this limitation, we develop a local-aggregation function, a sharable nonlinear operation, to aggregate permutation-unordered and dimension-unequal local inputs on non-Euclidean domains. In the context of the function approximation theory, the local-aggregation function is parameterized with a group of orthonormal polynomials in an effective and efficient manner. By replacing the traditional convolution in CNNs with the parameterized local-aggregation function, Local-Aggregation Graph Networks (LAGNs) are readily established, which enable to fit nonlinear functions without activation functions and can be expediently trained with the standard back-propagation. Extensive experiments on various datasets strongly demonstrate the effectiveness and efficiency of LAGNs, leading to superior performance on numerous pattern recognition and machine learning tasks, including text categorization, molecular activity detection, taxi flow prediction, and image classification.

A Performance Evaluation of Local Features for Image-Based 3D Reconstruction.

This paper performs a comprehensive and comparative evaluation of the state-of-the-art local features for the task of image-based 3D reconstruction. The evaluated local features cover the recently developed ones by using powerful machine learning techniques and the elaborately designed handcrafted features. To obtain a comprehensive evaluation, we choose to include both float type features and binary ones. Meanwhile, two kinds of datasets have been used in this evaluation. One is a dataset of many different scene types with groundtruth 3D points, containing images of different scenes captured at fixed positions, for quantitative performance evaluation of different local features in the controlled image capturing situation. The other dataset contains Internet scale image sets of several landmarks with a lot of unrelated images, which is used for qualitative performance evaluation of different local features in the free image collection situation. Our experimental results show that binary features are competent to reconstruct scenes from controlled image sequences with only a fraction of processing time compared to using float type features. However, for the case of a large scale image set with many distracting images, float type features show a clear advantage over binary ones. Currently, the most traditional SIFT is very stable with regard to scene types in this specific task and produces very competitive reconstruction results among all the evaluated local features. Meanwhile, although the learned binary features are not as competitive as the handcrafted ones, learning float type features with CNN is promising but still requires much effort in the future.

Nonlinear Asymmetric Multi-Valued Hashing.

Most existing hashing methods resort to binary codes for large scale similarity search, owing to the high efficiency of computation and storage. However, binary codes lack enough capability in similarity preservation, resulting in less desirable performance. To address this issue, we propose Nonlinear Asymmetric Multi-Valued Hashing (NAMVH) supported by two distinct non-binary embeddings. Specifically, a real-valued embedding is used for representing the newly-coming query by an ideally nonlinear transformation. Besides, a multi-integer-embedding is employed for compressing the whole database, which is modeled by Binary Sparse Representation (BSR) with fixed sparsity. With these two non-binary embeddings, NAMVH preserves more precise similarities between data points and enables access to the incremental extension with database samples evolving dynamically. To perform meaningful asymmetric similarity computation for efficient semantic search, these embeddings are jointly learnt by preserving the pairwise label-based similarity. Technically, this results in a mixed integer programming problem, which is efficiently solved by a well-designed alternative optimization method. Extensive experiments on seven large scale datasets demonstrate that our approach not only outperforms the existing binary hashing methods in search accuracy, but also retains their query and storage efficiency.

In Defense of Locality-Sensitive Hashing.

Hashing-based semantic similarity search is becoming increasingly important for building large-scale content-based retrieval system. The state-of-the-art supervised hashing techniques use flexible two-step strategy to learn hash functions. The first step learns binary codes for training data by solving binary optimization problems with millions of variables, thus usually requiring intensive computations. Despite simplicity and efficiency, locality-sensitive hashing (LSH) has never been recognized as a good way to generate such codes due to its poor performance in traditional approximate neighbor search. We claim in this paper that the true merit of LSH lies in transforming the semantic labels to obtain the binary codes, resulting in an effective and efficient two-step hashing framework. Specifically, we developed the locality-sensitive two-step hashing (LS-TSH) that generates the binary codes through LSH rather than any complex optimization technique. Theoretically, with proper assumption, LS-TSH is actually a useful LSH scheme, so that it preserves the label-based semantic similarity and possesses sublinear query complexity for hash lookup. Experimentally, LS-TSH could obtain comparable retrieval accuracy with state of the arts with two to three orders of magnitudes faster training speed.

Groupwise Retargeted Least-Squares Regression.

In this brief, we propose a new groupwise retargeted least squares regression (GReLSR) model for multicategory classification. The main motivation behind GReLSR is to utilize an additional regularization to restrict the translation values of ReLSR, so that they should be similar within same class. By analyzing the regression targets of ReLSR, we propose a new formulation of ReLSR, where the translation values are expressed explicitly. On the basis of the new formulation, discriminative least-squares regression can be regarded as a special case of ReLSR with zero translation values. Moreover, a groupwise constraint is added to ReLSR to form the new GReLSR model. Extensive experiments on various machine leaning data sets illustrate that our method outperforms the current state-of-the-art approaches.

MSDLSR: Margin Scalable Discriminative Least Squares Regression for Multicategory Classification.

In this brief, we propose a new margin scalable discriminative least squares regression (MSDLSR) model for multicategory classification. The main motivation behind the MSDLSR is to explicitly control the margin of DLSR model. We first prove that the DLSR is a relaxation of the traditional L2 -support vector machine. Based on this fact, we further provide a theorem on the margin of DLSR. With this theorem, we add an explicit constraint on DLSR to restrict the number of zeros of dragging values, so as to control the margin of DLSR. The new model is called MSDLSR. Theoretically, we analyze the determination of the margin and support vectors of MSDLSR. Extensive experiments illustrate that our method outperforms the current state-of-the-art approaches on various machine leaning and real-world data sets.

Layer-Wise Floorplan Extraction for Automatic Urban Building Reconstruction.

Urban building reconstruction is an important step for urban digitization and realisticvisualization. In this paper, we propose a novel automatic method to recover urban building geometry from 3D point clouds. The proposed method is suitable for buildings composed of planar polygons and aligned with the gravity direction, which are quite common in the city. Our key observation is that the building shapes are usually piecewise constant along the gravity direction and determined by several dominant shapes. Based on this observation, we formulate building reconstruction as an energy minimization problem under the Markov Random Field (MRF) framework. Specifically, point clouds are first cutinto a sequence of slices along the gravity direction. Then, floorplans are reconstructed by extracting boundaries of these slices, among which dominant floorplans are extracted and propagated to other floors via MRF. To guarantee correct propagation, a new distance measurement for floorplans is designed, which first encodes floorplans into strings and then calculates distances between their corresponding strings. Additionally, an image based editing method is also proposed to recover detailed window structures. Experimental results on both synthetic and real data sets have validated the effectiveness of our method.