arXiv subjects

Jiong Zhang

Publications and source records attributed to Jiong Zhang.

35 records · Page 2Linked to original sources

arXiv2022

Sparse-based Domain Adaptation Network for OCTA Image Super-Resolution Reconstruction

Retinal Optical Coherence Tomography Angiography (OCTA) with high-resolution is important for the quantification and analysis of retinal vasculature. However, the resolution of OCTA images is inversely proportional to the field of view at the same sampling frequency, which is not conducive to clinicians for analyzing larger vascular areas. In this paper, we propose a novel Sparse-based domain Adaptation Super-Resolution network (SASR) for the reconstruction of realistic 6x6 mm2/low-resolution (LR) OCTA images to high-resolution (HR) representations. To be more specific, we first perform a simple degradation of the 3x3 mm2/high-resolution (HR) image to obtain the synthetic LR image. An efficient registration method is then employed to register the synthetic LR with its corresponding 3x3 mm2 image region within the 6x6 mm2 image to obtain the cropped realistic LR image. We then propose a multi-level super-resolution model for the fully-supervised reconstruction of the synthetic data, guiding the reconstruction of the realistic LR images through a generative-adversarial strategy that allows the synthetic and realistic LR images to be unified in the feature domain. Finally, a novel sparse edge-aware loss is designed to dynamically optimize the vessel edge structure. Extensive experiments on two OCTA sets have shown that our method performs better than state-of-the-art super-resolution reconstruction methods. In addition, we have investigated the performance of the reconstruction results on retina structure segmentations, which further validate the effectiveness of our approach.

eess.IV↗

arXiv2022

Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction

Learning on graphs has attracted significant attention in the learning community due to numerous real-world applications. In particular, graph neural networks (GNNs), which take numerical node features and graph structure as inputs, have been shown to achieve state-of-the-art performance on various graph-related learning tasks. Recent works exploring the correlation between numerical node features and graph structure via self-supervised learning have paved the way for further performance improvements of GNNs. However, methods used for extracting numerical node features from raw data are still graph-agnostic within standard GNN pipelines. This practice is sub-optimal as it prevents one from fully utilizing potential correlations between graph topology and node attributes. To mitigate this issue, we propose a new self-supervised learning framework, Graph Information Aided Node feature exTraction (GIANT). GIANT makes use of the eXtreme Multi-label Classification (XMC) formalism, which is crucial for fine-tuning the language model based on graph information, and scales to large datasets. We also provide a theoretical analysis that justifies the use of XMC over link prediction and motivates integrating XR-Transformers, a powerful method for solving XMC problems, into the GIANT framework. We demonstrate the superior performance of GIANT over the standard GNN pipeline on Open Graph Benchmark datasets: For example, we improve the accuracy of the top-ranked method GAMLP from $68.25\%$ to $69.67\%$, SGC from $63.29\%$ to $66.10\%$ and MLP from $47.24\%$ to $61.10\%$ on the ogbn-papers100M dataset by leveraging GIANT.

cs.LG↗

arXiv2022

PECOS: Prediction for Enormous and Correlated Output Spaces

Many large-scale applications amount to finding relevant results from an enormous output space of potential candidates. For example, finding the best matching product from a large catalog or suggesting related search phrases on a search engine. The size of the output space for these problems can range from millions to billions, and can even be infinite in some applications. Moreover, training data is often limited for the long-tail items in the output space. Fortunately, items in the output space are often correlated thereby presenting an opportunity to alleviate the data sparsity issue. In this paper, we propose the Prediction for Enormous and Correlated Output Spaces (PECOS) framework, a versatile and modular machine learning framework for solving prediction problems for very large output spaces, and apply it to the eXtreme Multilabel Ranking (XMR) problem: given an input instance, find and rank the most relevant items from an enormous but fixed and finite output space. We propose a three phase framework for PECOS: (i) in the first phase, PECOS organizes the output space using a semantic indexing scheme, (ii) in the second phase, PECOS uses the indexing to narrow down the output space by orders of magnitude using a machine learned matching scheme, and (iii) in the third phase, PECOS ranks the matched items using a final ranking scheme. The versatility and modularity of PECOS allows for easy plug-and-play of various choices for the indexing, matching, and ranking phases. We also develop very fast inference procedures which allow us to perform XMR predictions in real time; for example, inference takes less than 1 millisecond per input on the dataset with 2.8 million labels. The PECOS software is available at https://libpecos.org.

cs.LG↗

arXiv2021

Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

Extreme multi-label text classification (XMC) seeks to find relevant labels from an extreme large label collection for a given text input. Many real-world applications can be formulated as XMC problems, such as recommendation systems, document tagging and semantic search. Recently, transformer based XMC methods, such as X-Transformer and LightXML, have shown significant improvement over other XMC methods. Despite leveraging pre-trained transformer models for text representation, the fine-tuning procedure of transformer models on large label space still has lengthy computational time even with powerful GPUs. In this paper, we propose a novel recursive approach, XR-Transformer to accelerate the procedure through recursively fine-tuning transformer models on a series of multi-resolution objectives related to the original XMC objective function. Empirical results show that XR-Transformer takes significantly less training time compared to other transformer-based XMC models while yielding better state-of-the-art results. In particular, on the public Amazon-3M dataset with 3 million labels, XR-Transformer is not only 20x faster than X-Transformer but also improves the Precision@1 from 51% to 54%.

cs.LG↗

arXiv2021

Data-Driven Electron Microscopy: Electron Diffraction Imaging of Materials Structural Properties

Transmission electron diffraction is a powerful and versatile structural probe for the characterization of a broad range of materials, from nanocrystalline thin films to single crystals. With recent developments in fast electron detectors and efficient computer algorithms, it now becomes possible to collect unprecedently large datasets of diffraction patterns (DPs) and process DPs to extract crystallographic information to form images or tomograms based on crystal structural properties, giving rise to data-driven electron microscopy. Critical to this kind of imaging is the type of crystallographic information being collected, which can be achieved with a judicious choice of electron diffraction techniques, and the efficiency and accuracy of DP processing, which requires the development of new algorithms. Here, we review recent progress made in data collection, new algorithms, and automated electron DP analysis. These progresses will be highlighted using application examples in materials research. Future opportunities based on smart sampling and machine learning are also discussed.

cond-mat.mtrl-sci↗

arXiv2021

Extreme Multi-label Learning for Semantic Matching in Product Search

We consider the problem of semantic matching in product search: given a customer query, retrieve all semantically related products from a huge catalog of size 100 million, or more. Because of large catalog spaces and real-time latency constraints, semantic matching algorithms not only desire high recall but also need to have low latency. Conventional lexical matching approaches (e.g., Okapi-BM25) exploit inverted indices to achieve fast inference time, but fail to capture behavioral signals between queries and products. In contrast, embedding-based models learn semantic representations from customer behavior data, but the performance is often limited by shallow neural encoders due to latency constraints. Semantic product search can be viewed as an eXtreme Multi-label Classification (XMC) problem, where customer queries are input instances and products are output labels. In this paper, we aim to improve semantic product search by using tree-based XMC models where inference time complexity is logarithmic in the number of products. We consider hierarchical linear models with n-gram features for fast real-time inference. Quantitatively, our method maintains a low latency of 1.25 milliseconds per query and achieves a 65% improvement of Recall@100 (60.9% v.s. 36.8%) over a competing embedding-based DSSM model. Our model is robust to weight pruning with varying thresholds, which can flexibly meet different system requirements for online deployments. Qualitatively, our method can retrieve products that are complementary to existing product search system and add diversity to the match set.

cs.IR↗

arXiv2021

Training artificial neural networks for precision orientation and strain mapping using 4D electron diffraction datasets

Techniques for training artificial neural networks (ANNs) and convolutional neural networks (CNNs) using simulated dynamical electron diffraction patterns are described. The premise is based on the following facts. First, given a suitable crystal structure model and scattering potential, electron diffraction patterns can be simulated accurately using dynamical diffraction theory. Secondly, using simulated diffraction patterns as input, ANNs can be trained for the determination of crystal structural properties, such as crystal orientation and local strain. Further, by applying the trained ANNs to four-dimensional diffraction datasets (4D-DD) collected using the scanning electron nanodiffraction (SEND) or 4D scanning transmission electron microscopy (4D-STEM) techniques, the crystal structural properties can be mapped at high spatial resolution. Here, we demonstrate the ANN-enabled possibilities for the analysis of crystal orientation and strain at high precision and benchmark the performance of ANNs and CNNs by comparing with previous methods. A factor of thirty improvement in angular resolution at 0.009 degrees (0.16 mrad) for orientation mapping, sensitivity at 0.04% or less for strain mapping, and improvements in computational performance are demonstrated.

cond-mat.mes-hall↗

arXiv2021

3D Vessel Reconstruction in OCT-Angiography via Depth Map Estimation

Optical Coherence Tomography Angiography (OCTA) has been increasingly used in the management of eye and systemic diseases in recent years. Manual or automatic analysis of blood vessel in 2D OCTA images (en face angiograms) is commonly used in clinical practice, however it may lose rich 3D spatial distribution information of blood vessels or capillaries that are useful for clinical decision-making. In this paper, we introduce a novel 3D vessel reconstruction framework based on the estimation of vessel depth maps from OCTA images. First, we design a network with structural constraints to predict the depth of blood vessels in OCTA images. In order to promote the accuracy of the predicted depth map at both the overall structure- and pixel- level, we combine MSE and SSIM loss as the training loss function. Finally, the 3D vessel reconstruction is achieved by utilizing the estimated depth map and 2D vessel segmentation results. Experimental results demonstrate that our method is effective in the depth prediction and 3D vessel reconstruction for OCTA images.% results may be used to guide subsequent vascular analysis

eess.IV↗

arXiv2020

ROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model

Optical Coherence Tomography Angiography (OCT-A) is a non-invasive imaging technique, and has been increasingly used to image the retinal vasculature at capillary level resolution. However, automated segmentation of retinal vessels in OCT-A has been under-studied due to various challenges such as low capillary visibility and high vessel complexity, despite its significance in understanding many eye-related diseases. In addition, there is no publicly available OCT-A dataset with manually graded vessels for training and validation. To address these issues, for the first time in the field of retinal image analysis we construct a dedicated Retinal OCT-A SEgmentation dataset (ROSE), which consists of 229 OCT-A images with vessel annotations at either centerline-level or pixel level. This dataset has been released for public access to assist researchers in the community in undertaking research in related topics. Secondly, we propose a novel Split-based Coarse-to-Fine vessel segmentation network (SCF-Net), with the ability to detect thick and thin vessels separately. In the SCF-Net, a split-based coarse segmentation (SCS) module is first introduced to produce a preliminary confidence map of vessels, and a split-based refinement (SRN) module is then used to optimize the shape/contour of the retinal microvasculature. Thirdly, we perform a thorough evaluation of the state-of-the-art vessel segmentation models and our SCF-Net on the proposed ROSE dataset. The experimental results demonstrate that our SCF-Net yields better vessel segmentation performance in OCT-A than both traditional methods and other deep learning methods.

eess.IV↗

arXiv2019

AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Deep neural networks have yielded superior performance in many applications; however, the gradient computation in a deep model with millions of instances lead to a lengthy training process even with modern GPU/TPU hardware acceleration. In this paper, we propose AutoAssist, a simple framework to accelerate training of a deep neural network. Typically, as the training procedure evolves, the amount of improvement in the current model by a stochastic gradient update on each instance varies dynamically. In AutoAssist, we utilize this fact and design a simple instance shrinking operation, which is used to filter out instances with relatively low marginal improvement to the current model; thus the computationally intensive gradient computations are performed on informative instances as much as possible. We prove that the proposed technique outperforms vanilla SGD with existing importance sampling approaches for linear SVM problems, and establish an O(1/k) convergence for strongly convex problems. In order to apply the proposed techniques to accelerate training of deep models, we propose to jointly train a very lightweight Assistant network in addition to the original deep network referred to as Boss. The Assistant network is designed to gauge the importance of a given instance with respect to the current Boss such that a shrinking operation can be applied in the batch generator. With careful design, we train the Boss and Assistant in a nonblocking and asynchronous fashion such that overhead is minimal. We demonstrate that AutoAssist reduces the number of epochs by 40% for training a ResNet to reach the same test accuracy on an image classification data set and saves 30% training time needed for a transformer model to yield the same BLEU scores on a translation dataset.

cs.LG↗

arXiv2018

Minimal Paths for Tubular Structure Segmentation with Coherence Penalty and Adaptive Anisotropy

The minimal path method has proven to be particularly useful and efficient in tubular structure segmentation applications. In this paper, we propose a new minimal path model associated with a dynamic Riemannian metric embedded with an appearance feature coherence penalty and an adaptive anisotropy enhancement term. The features that characterize the appearance and anisotropy properties of a tubular structure are extracted through the associated orientation score. The proposed dynamic Riemannian metric is updated in the course of the geodesic distance computation carried out by the efficient single-pass fast marching method. Compared to state-of-the-art minimal path models, the proposed minimal path model is able to extract the desired tubular structures from a complicated vessel tree structure. In addition, we propose an efficient prior path-based method to search for vessel radius value at each centerline position of the target. Finally, we perform the numerical experiments on both synthetic and real images. The quantitive validation is carried out on retinal vessel images. The results indicate that the proposed model indeed achieves a promising performance.

cs.CV↗

arXiv2018

Extreme Stochastic Variational Inference: Distributed and Asynchronous

Stochastic variational inference (SVI), the state-of-the-art algorithm for scaling variational inference to large-datasets, is inherently serial. Moreover, it requires the parameters to fit in the memory of a single processor; this is problematic when the number of parameters is in billions. In this paper, we propose extreme stochastic variational inference (ESVI), an asynchronous and lock-free algorithm to perform variational inference for mixture models on massive real world datasets. ESVI overcomes the limitations of SVI by requiring that each processor only access a subset of the data and a subset of the parameters, thus providing data and model parallelism simultaneously. We demonstrate the effectiveness of ESVI by running Latent Dirichlet Allocation (LDA) on UMBC-3B, a dataset that has a vocabulary of 3 million and a token size of 3 billion. In our experiments, we found that ESVI not only outperforms VI and SVI in wallclock-time, but also achieves a better quality solution. In addition, we propose a strategy to speed up computation and save memory when fitting large number of topics.

stat.ML↗

arXiv2018

Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

Vanishing and exploding gradients are two of the main obstacles in training deep neural networks, especially in capturing long range dependencies in recurrent neural networks~(RNNs). In this paper, we present an efficient parametrization of the transition matrix of an RNN that allows us to stabilize the gradients that arise in its training. Specifically, we parameterize the transition matrix by its singular value decomposition(SVD), which allows us to explicitly track and control its singular values. We attain efficiency by using tools that are common in numerical linear algebra, namely Householder reflectors for representing the orthogonal matrices that arise in the SVD. By explicitly controlling the singular values, our proposed Spectral-RNN method allows us to easily solve the exploding gradient problem and we observe that it empirically solves the vanishing gradient issue to a large extent. We note that the SVD parameterization can be used for any rectangular weight matrix, hence it can be easily extended to any deep neural network, such as a multi-layer perceptron. Theoretically, we demonstrate that our parameterization does not lose any expressive power, and show how it controls generalization of RNN for the classification task. %, and show how it potentially makes the optimization process easier. Our extensive experimental results also demonstrate that the proposed framework converges faster, and has good generalization, especially in capturing long range dependencies, as shown on the synthetic addition and copy tasks, as well as on MNIST and Penn Tree Bank data sets.

cs.LG↗

arXiv2018

Learning Long Term Dependencies via Fourier Recurrent Units

It is a known fact that training recurrent neural networks for tasks that have long term dependencies is challenging. One of the main reasons is the vanishing or exploding gradient problem, which prevents gradient information from propagating to early layers. In this paper we propose a simple recurrent architecture, the Fourier Recurrent Unit (FRU), that stabilizes the gradients that arise in its training while giving us stronger expressive power. Specifically, FRU summarizes the hidden states $h^{(t)}$ along the temporal dimension with Fourier basis functions. This allows gradients to easily reach any layer due to FRU's residual learning structure and the global support of trigonometric functions. We show that FRU has gradient lower and upper bounds independent of temporal dimension. We also show the strong expressivity of sparse Fourier basis, from which FRU obtains its strong expressive power. Our experimental study also demonstrates that with fewer parameters the proposed architecture outperforms other recurrent architectures on many tasks.

cs.LG↗

arXiv2017

Retinal Microaneurysms Detection using Local Convergence Index Features

Retinal microaneurysms are the earliest clinical sign of diabetic retinopathy disease. Detection of microaneurysms is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of microaneurysms in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (RGB and SLO) using five publicly available datasets including the Retinopathy Online Challenge's dataset. The proposed method achieves an average sensitivity score of 0.471 on the ROC dataset outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other four datasets demonstrate the effectiveness and robustness of the proposed microaneurysms detection method regardless of different image resolutions and modalities.

cs.CV↗

arXiv2016

Retrieving challenging vessel connections in retinal images by line co-occurrence statistics

Natural images contain often curvilinear structures, which might be disconnected, or partly occluded. Recovering the missing connection of disconnected structures is an open issue and needs appropriate geometric reasoning. We propose to find line co-occurrence statistics from the centerlines of blood vessels in retinal images and show its remarkable similarity to a well-known probabilistic model for the connectivity pattern in the primary visual cortex. Furthermore, the probabilistic model is trained from the data via statistics and used for automated grouping of interrupted vessels in a spectral clustering based approach. Several challenging image patches are investigated around junction points, where successful results indicate the perfect match of the trained model to the profiles of blood vessels in retinal images. Also, comparisons among several statistical models obtained from different datasets reveals their high similarity i.e., they are independent of the dataset. On top of that, the best approximation of the statistical model with the symmetrized extension of the probabilistic model on the projective line bundle is found with a least square error smaller than 2%. Apparently, the direction process on the projective line bundle is a good continuation model for vessels in retinal images.

cs.CV↗

arXiv2016

Numerical Approaches for Linear Left-invariant Diffusions on SE(2), their Comparison to Exact Solutions, and their Applications in Retinal Imaging

Left-invariant PDE-evolutions on the roto-translation group $SE(2)$ (and their resolvent equations) have been widely studied in the fields of cortical modeling and image analysis. They include hypo-elliptic diffusion (for contour enhancement) proposed by Citti & Sarti, and Petitot, and they include the direction process (for contour completion) proposed by Mumford. This paper presents a thorough study and comparison of the many numerical approaches, which, remarkably, is missing in the literature. Existing numerical approaches can be classified into 3 categories: Finite difference methods, Fourier based methods (equivalent to $SE(2)$-Fourier methods), and stochastic methods (Monte Carlo simulations). There are also 3 types of exact solutions to the PDE-evolutions that were derived explicitly (in the spatial Fourier domain) in previous works by Duits and van Almsick in 2005. Here we provide an overview of these 3 types of exact solutions and explain how they relate to each of the 3 numerical approaches. We compute relative errors of all numerical approaches to the exact solutions, and the Fourier based methods show us the best performance with smallest relative errors. We also provide an improvement of Mathematica algorithms for evaluating Mathieu-functions, crucial in implementations of the exact solutions. Furthermore, we include an asymptotical analysis of the singularities within the kernels and we propose a probabilistic extension of underlying stochastic processes that overcomes the singular behavior in the origin of time-integrated kernels. Finally, we show retinal imaging applications of combining left-invariant PDE-evolutions with invertible orientation scores.

math.NA↗