arXiv subjects

Binh Nguyen

Publications and source records attributed to Binh Nguyen.

34 records · Page 2Linked to original sources

arXiv2024

CovHuSeg: An Enhanced Approach for Kidney Pathology Segmentation

Segmentation has long been essential in computer vision due to its numerous real-world applications. However, most traditional deep learning and machine learning models need help to capture geometric features such as size and convexity of the segmentation targets, resulting in suboptimal outcomes. To resolve this problem, we propose using a CovHuSeg algorithm to solve the problem of kidney glomeruli segmentation. This simple post-processing method is specified to adapt to the segmentation of ball-shaped anomalies, including the glomerulus. Unlike other post-processing methods, the CovHuSeg algorithm assures that the outcome mask does not have holes in it or comes in unusual shapes that are impossible to be the shape of a glomerulus. We illustrate the effectiveness of our method by experimenting with multiple deep-learning models in the context of segmentation on kidney pathology images. The results show that all models have increased accuracy when using the CovHuSeg algorithm.

eess.IV↗

arXiv2024

Deep-Wide Learning Assistance for Insect Pest Classification

Accurate insect pest recognition plays a critical role in agriculture. It is a challenging problem due to the intricate characteristics of insects. In this paper, we present DeWi, novel learning assistance for insect pest classification. With a one-stage and alternating training strategy, DeWi simultaneously improves several Convolutional Neural Networks in two perspectives: discrimination (by optimizing a triplet margin loss in a supervised training manner) and generalization (via data augmentation). From that, DeWi can learn discriminative and in-depth features of insect pests (deep) yet still generalize well to a large number of insect categories (wide). Experimental results show that DeWi achieves the highest performances on two insect pest classification benchmarks (76.44\% accuracy on the IP102 dataset and 99.79\% accuracy on the D0 dataset, respectively). In addition, extensive evaluations and ablation studies are conducted to thoroughly investigate our DeWi and demonstrate its superiority. Our source code is available at https://github.com/toannguyen1904/DeWi.

cs.CV↗

arXiv2024

Generative Conditional Distributions by Neural (Entropic) Optimal Transport

Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural entropic optimal transport method designed to effectively learn generative models of conditional distributions, particularly in scenarios characterized by limited sample sizes. Our method relies on the minimax training of two neural networks: a generative network parametrizing the inverse cumulative distribution functions of the conditional distributions and another network parametrizing the conditional Kantorovich potential. To prevent overfitting, we regularize the objective function by penalizing the Lipschitz constant of the network output. Our experiments on real-world datasets show the effectiveness of our algorithm compared to state-of-the-art conditional distribution learning techniques. Our implementation can be found at https://github.com/nguyenngocbaocmt02/GENTLE.

cs.LG↗

arXiv2024

Spatially temporally distributed informative path planning for multi-robot systems

This paper investigates the problem of informative path planning for a mobile robotic sensor network in spatially temporally distributed mapping. The robots are able to gather noisy measurements from an area of interest during their movements to build a Gaussian Process (GP) model of a spatio-temporal field. The model is then utilized to predict the spatio-temporal phenomenon at different points of interest. To spatially and temporally navigate the group of robots so that they can optimally acquire maximal information gains while their connectivity is preserved, we propose a novel multistep prediction informative path planning optimization strategy employing our newly defined local cost functions. By using the dual decomposition method, it is feasible and practical to effectively solve the optimization problem in a distributed manner. The proposed method was validated through synthetic experiments utilizing real-world data sets.

cs.RO↗

arXiv2024

Bellman Optimal Stepsize Straightening of Flow-Matching Models

Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the finetuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Stepsize Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programming algorithm that optimizes the stepsizes of the pretrained network. Then, it refines the velocity network to match the optimal step sizes, aiming to straighten the generation paths. Extensive experimental evaluations across image generation tasks demonstrate the efficacy of BOSS in terms of both resource utilization and image quality. Our results reveal that BOSS achieves substantial gains in efficiency while maintaining competitive sample quality, effectively bridging the gap between low-resource constraints and the demanding requirements of flow-matching generative models. Our paper also fortifies the responsible development of artificial intelligence, offering a more sustainable generative model that reduces computational costs and environmental footprints. Our code can be found at https://github.com/nguyenngocbaocmt02/BOSS.

cs.CV↗

arXiv2023

Flow Matching in Latent Space

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods still face the challenges of expensive computing and a large number of function evaluations of off-the-shelf solvers in the pixel space. Furthermore, although latent-based generative methods have shown great success in recent years, this particular model type remains underexplored in this area. In this work, we propose to apply flow matching in the latent spaces of pretrained autoencoders, which offers improved computational efficiency and scalability for high-resolution image synthesis. This enables flow-matching training on constrained computational resources while maintaining their quality and flexibility. Additionally, our work stands as a pioneering contribution in the integration of various conditions into flow matching for conditional generation tasks, including label-conditioned image generation, image inpainting, and semantic-to-image generation. Through extensive experiments, our approach demonstrates its effectiveness in both quantitative and qualitative results on various datasets, such as CelebA-HQ, FFHQ, LSUN Church & Bedroom, and ImageNet. We also provide a theoretical control of the Wasserstein-2 distance between the reconstructed latent flow distribution and true data distribution, showing it is upper-bounded by the latent flow matching objective. Our code will be available at https://github.com/VinAIResearch/LFM.git.

cs.CV↗

arXiv2023

Application of Self-Supervised Learning to MICA Model for Reconstructing Imperfect 3D Facial Structures

In this study, we emphasize the integration of a pre-trained MICA model with an imperfect face dataset, employing a self-supervised learning approach. We present an innovative method for regenerating flawed facial structures, yielding 3D printable outputs that effectively support physicians in their patient treatment process. Our results highlight the model's capacity for concealing scars and achieving comprehensive facial reconstructions without discernible scarring. By capitalizing on pre-trained models and necessitating only a few hours of supplementary training, our methodology adeptly devises an optimal model for reconstructing damaged and imperfect facial features. Harnessing contemporary 3D printing technology, we institute a standardized protocol for fabricating realistic, camouflaging mask models for patients in a laboratory environment.

cs.CV↗

arXiv2023

Encrypted Observer-based Control for Linear Continuous-Time Systems

This paper is concerned with the stability analysis of encrypted observer-based control for linear continuous-time systems. Since conventional encryption has limited ability to deploy in continuous-time integral computation, our work presents systematically a new design of encryption for a continuous-time observer-based control scheme. To be specific, in this paper, both control parameters and signals are encrypted by the learning-with-errors (LWE) encryption to avoid data eavesdropping. Furthermore, we propose encrypted computations for the observer-based controller based on its discrete-time model, and present a continuous-time virtual dynamics of the controller for further stability analysis. Accordingly, we present novel stability criteria by introducing linear matrix inequalities (LMIs)-based conditions associated with quantization gains and sampling intervals. The established stability criteria with theoretical proofs based on a discontinuous Lyapunov functional possibly provide a way to select quantization gains and sampling intervals to guarantee the stability of the closed-loop system. Numerical results on DC motor control corresponding to several quantization gains and sampling intervals demonstrate the validity of our method.

eess.SY↗

arXiv2023

Ontology-based Solution for Building an Intelligent Searching System on Traffic Law Documents

In this paper, an ontology-based approach is used to organize the knowledge base of legal documents in road traffic law. This knowledge model is built by the improvement of ontology Rela-model. In addition, several searching problems on traffic law are proposed and solved based on the legal knowledge base. The intelligent search system on Vietnam road traffic law is constructed by applying the method. The searching system can help users to find concepts and definitions in road traffic law. Moreover, it can also determine penalties and fines for violations in the traffic. The experiment results show that the system is efficient for users' typical searching and is emerging for usage in the real-world.

cs.IR↗

arXiv2022

Higher-order magnetic anisotropy in soft-hard magnetic materials

We have computationally studied the properties of higher-order magnetic anisotropy constants in an L10/A1-FePt coreshell system which is characterized by a strong second-order 2-ion Fe-Pt anisotropy component. We show that the coreshell structure induces an unexpected fourth-order anisotropy constant K2 the magnitude of which varies non-monotonically with the core-size ratio R reaching a peak at R = 0.50. Furthermore, we find that K2 scales with the normalized magnetization by (M/Ms)^2.2 at temperatures below the Curie temperature - a remarkable deviation from the established Callen-Callen theory which instead predicts a scaling exponent of 10. We construct an analytic model which demonstrates K2 arises from the canting of the core and shell magnetization, and successfully reproduces and justifies the scaling exponent obtained from numerical simulation.

cond-mat.mtrl-sci↗

arXiv2021

Co-Factorization Model for Collaborative Filtering with Session-based Data

Matrix factorization (MF) is a common method for collaborative filtering. MF represents user preferences and item attributes by latent factors. Despite that MF is a powerful method, it suffers from not be able to identifying strong associations of closely related items. In this work, we propose a method for matrix factorization that can reflect the localized relationships between strong related items into the latent representations of items. We do it by combine two worlds: MF for collaborative filtering and item2vec for item-embedding. The proposed method is able to exploit item-item relations. Our experiments on several datasets demonstrates a better performance with the previous work.

cs.IR↗

arXiv2021

Learning Representations from Product Titles for Modeling Shopping Transactions

Shopping transaction analysis is important for understanding the shopping behaviors of customers. Existing models such as association rules are poor at modeling products that have short purchase histories and cannot be applied to new products (the cold-start problem). In this paper, we propose BASTEXT, an efficient model of shopping baskets and the texts associated with the products (e.g., product titles). The model's goal is to learn the product representations from the textual contents to capture the relationships between the products in the baskets. Given the products already in a basket, a classifier identifies whether a potential product is relevant to the basket based on their vector representations. This relevancy enables us to learn high-quality representations of the products. The experiments demonstrate that BASTEXT can efficiently model millions of baskets and that it outperforms the state-of-the-art methods in the next product recommendation task. We also show that BASTEXT is a strong baseline for keyword-based product search.

cs.IR↗

arXiv2021

Bayesian Pool-based Active Learning With Abstention Feedbacks

We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the classification problem and the unknown abstention rate at the same time. These are achieved by simply incorporating the estimated abstention rate into the greedy criteria. We prove that both of our algorithms have near-optimality guarantees: they respectively achieve a ${(1-\frac{1}{e})}$ constant factor approximation of the optimal expected or worst-case value of a useful utility function. Our experiments show the algorithms perform well in various practical scenarios.

stat.ML↗

arXiv2020

Bayesian Active Learning With Abstention Feedbacks

We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the classification problem and the unknown abstention rate at the same time. These are achieved by simply incorporating the estimated average abstention rate into the greedy criteria. We prove that both algorithms have near-optimality guarantees: they respectively achieve a ${(1-\frac{1}{e})}$ constant factor approximation of the optimal expected or worst-case value of a useful utility function. Our experiments show the algorithms perform well in various practical scenarios.

cs.LG↗

arXiv2019

Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging

In recent years, studies on automatic speech recognition (ASR) have shown outstanding results that reach human parity on short speech segments. However, there are still difficulties in standardizing the output of ASR such as capitalization and punctuation restoration for long-speech transcription. The problems obstruct readers to understand the ASR output semantically and also cause difficulties for natural language processing models such as NER, POS and semantic parsing. In this paper, we propose a method to restore the punctuation and capitalization for long-speech ASR transcription. The method is based on Transformer models and chunk merging that allows us to (1), build a single model that performs punctuation and capitalization in one go, and (2), perform decoding in parallel while improving the prediction accuracy. Experiments on British National Corpus showed that the proposed approach outperforms existing methods in both accuracy and decoding speed.

cs.CL↗

arXiv2018

Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains

Fabric is a modular and extensible open-source system for deploying and operating permissioned blockchains and one of the Hyperledger projects hosted by the Linux Foundation (www.hyperledger.org). Fabric is the first truly extensible blockchain system for running distributed applications. It supports modular consensus protocols, which allows the system to be tailored to particular use cases and trust models. Fabric is also the first blockchain system that runs distributed applications written in standard, general-purpose programming languages, without systemic dependency on a native cryptocurrency. This stands in sharp contrast to existing blockchain platforms that require "smart-contracts" to be written in domain-specific languages or rely on a cryptocurrency. Fabric realizes the permissioned model using a portable notion of membership, which may be integrated with industry-standard identity management. To support such flexibility, Fabric introduces an entirely novel blockchain design and revamps the way blockchains cope with non-determinism, resource exhaustion, and performance attacks. This paper describes Fabric, its architecture, the rationale behind various design decisions, its most prominent implementation aspects, as well as its distributed application programming model. We further evaluate Fabric by implementing and benchmarking a Bitcoin-inspired digital currency. We show that Fabric achieves end-to-end throughput of more than 3500 transactions per second in certain popular deployment configurations, with sub-second latency, scaling well to over 100 peers.

cs.DC↗