arXiv subjects

Seonho Kim

Publications and source records attributed to Seonho Kim.

14 recordsLinked to original sources

arXiv2025

TUS-REC2024: A Challenge to Reconstruct 3D Freehand Ultrasound Without External Tracker

Trackerless freehand ultrasound reconstruction aims to reconstruct 3D volumes from sequences of 2D ultrasound images without relying on external tracking systems. By eliminating the need for optical or electromagnetic trackers, this approach offers a low-cost, portable, and widely deployable alternative to more expensive volumetric ultrasound imaging systems, particularly valuable in resource-constrained clinical settings. However, predicting long-distance transformations and handling complex probe trajectories remain challenging. The TUS-REC2024 Challenge establishes the first benchmark for trackerless 3D freehand ultrasound reconstruction by providing a large publicly available dataset, along with a baseline model and a rigorous evaluation framework. By the submission deadline, the Challenge had attracted 43 registered teams, of which 6 teams submitted 21 valid dockerized solutions. The submitted methods span a wide range of approaches, including the state space model, the recurrent model, the registration-driven volume refinement, the attention mechanism, and the physics-informed model. This paper provides a comprehensive background introduction and literature review in the field, presents an overview of the challenge design and dataset, and offers a comparative analysis of submitted methods across multiple evaluation metrics. These analyses highlight both the progress and the current limitations of state-of-the-art approaches in this domain and provide insights for future research directions. All data and code are publicly available to facilitate ongoing development and reproducibility. As a live and evolving benchmark, it is designed to be continuously iterated and improved. The Challenge was held at MICCAI 2024 and is organised again at MICCAI 2025, reflecting its sustained commitment to advancing this field.

eess.IV↗

arXiv2025

Probabilistic Variational Contrastive Learning

Deterministic embeddings learned by contrastive learning (CL) methods such as SimCLR and SupCon achieve state-of-the-art performance but lack a principled mechanism for uncertainty quantification. We propose Variational Contrastive Learning (VCL), a decoder-free framework that maximizes the evidence lower bound (ELBO) by interpreting the InfoNCE loss as a surrogate reconstruction term and adding a KL divergence regularizer to a uniform prior on the unit hypersphere. We model the approximate posterior $q_\theta(z|x)$ as a projected normal distribution, enabling the sampling of probabilistic embeddings. Our two instantiation--VSimCLR and VSupCon--replace deterministic embeddings with samples from $q_\theta(z|x)$ and incorporate a normalized KL term into the loss. Experiments on multiple benchmarks demonstrate that VCL mitigates dimensional collapse, enhances mutual information with class labels, and matches or outperforms deterministic baselines in classification accuracy, all the while providing meaningful uncertainty estimates through the posterior model. VCL thus equips contrastive learning with a probabilistic foundation, serving as a new basis for contrastive approaches.

cs.LG↗

arXiv2025

Learned Image Compression and Restoration for Digital Pathology

Digital pathology images play a crucial role in medical diagnostics, but their ultra-high resolution and large file sizes pose significant challenges for storage, transmission, and real-time visualization. To address these issues, we propose CLERIC, a novel deep learning-based image compression framework designed specifically for whole slide images (WSIs). CLERIC integrates a learnable lifting scheme and advanced convolutional techniques to enhance compression efficiency while preserving critical pathological details. Our framework employs a lifting-scheme transform in the analysis stage to decompose images into low- and high-frequency components, enabling more structured latent representations. These components are processed through parallel encoders incorporating Deformable Residual Blocks (DRB) and Recurrent Residual Blocks (R2B) to improve feature extraction and spatial adaptability. The synthesis stage applies an inverse lifting transform for effective image reconstruction, ensuring high-fidelity restoration of fine-grained tissue structures. We evaluate CLERIC on a digital pathology image dataset and compare its performance against state-of-the-art learned image compression (LIC) models. Experimental results demonstrate that CLERIC achieves superior rate-distortion (RD) performance, significantly reducing storage requirements while maintaining high diagnostic image quality. Our study highlights the potential of deep learning-based compression in digital pathology, facilitating efficient data management and long-term storage while ensuring seamless integration into clinical workflows and AI-assisted diagnostic systems. Code and models are available at: https://github.com/pnu-amilab/CLERIC.

cs.CV↗

arXiv2024

Sparse Max-Affine Regression

This paper presents Sparse Gradient Descent as a solution for variable selection in convex piecewise linear regression, where the model is given as the maximum of $k$-affine functions $ x \mapsto \max_{j \in [k]} \langle a_j^\star, x \rangle + b_j^\star$ for $j = 1,\dots,k$. Here, $\{ a_j^\star\}_{j=1}^k$ and $\{b_j^\star\}_{j=1}^k$ denote the ground-truth weight vectors and intercepts. A non-asymptotic local convergence analysis is provided for Sp-GD under sub-Gaussian noise when the covariate distribution satisfies the sub-Gaussianity and anti-concentration properties. When the model order and parameters are fixed, Sp-GD provides an $\epsilon$-accurate estimate given $\mathcal{O}(\max(\epsilon^{-2}\sigma_z^2,1)s\log(d/s))$ observations where $\sigma_z^2$ denotes the noise variance. This also implies the exact parameter recovery by Sp-GD from $\mathcal{O}(s\log(d/s))$ noise-free observations. The proposed initialization scheme uses sparse principal component analysis to estimate the subspace spanned by $\{ a_j^\star\}_{j=1}^k$, then applies an $r$-covering search to estimate the model parameters. A non-asymptotic analysis is presented for this initialization scheme when the covariates and noise samples follow Gaussian distributions. When the model order and parameters are fixed, this initialization scheme provides an $\epsilon$-accurate estimate given $\mathcal{O}(\epsilon^{-2}\max(\sigma_z^4,\sigma_z^2,1)s^2\log^4(d))$ observations. A new transformation named Real Maslov Dequantization (RMD) is proposed to transform sparse generalized polynomials into sparse max-affine models. The error decay rate of RMD is shown to be exponentially small in its temperature parameter. Furthermore, theoretical guarantees for Sp-GD are extended to the bounded noise model induced by RMD. Numerical Monte Carlo results corroborate theoretical findings for Sp-GD and the initialization scheme.

stat.ML↗

arXiv2024

Robust Phase Retrieval by Alternating Minimization

We consider a least absolute deviation (LAD) approach to the robust phase retrieval problem that aims to recover a signal from its absolute measurements corrupted with sparse noise. To solve the resulting non-convex optimization problem, we propose a robust alternating minimization (Robust-AM) derived as an unconstrained Gauss-Newton method. To solve the inner optimization arising in each step of Robust-AM, we adopt two computationally efficient methods for linear programs. We provide a non-asymptotic convergence analysis of these practical algorithms for Robust-AM under the standard Gaussian measurement assumption. These algorithms, when suitably initialized, are guaranteed to converge linearly to the ground truth at an order-optimal sample complexity with high probability while the support of sparse noise is arbitrarily fixed and the sparsity level is no larger than $1/4$. Additionally, through comprehensive numerical experiments on synthetic and image datasets, we show that Robust-AM outperforms existing methods for robust phase retrieval offering comparable theoretical performance

eess.SP↗

arXiv2023

Max-affine regression via first-order methods

We consider regression of a max-affine model that produces a piecewise linear model by combining affine models via the max function. The max-affine model ubiquitously arises in applications in signal processing and statistics including multiclass classification, auction problems, and convex regression. It also generalizes phase retrieval and learning rectifier linear unit activation functions. We present a non-asymptotic convergence analysis of gradient descent (GD) and mini-batch stochastic gradient descent (SGD) for max-affine regression when the model is observed at random locations following the sub-Gaussianity and an anti-concentration with additive sub-Gaussian noise. Under these assumptions, a suitably initialized GD and SGD converge linearly to a neighborhood of the ground truth specified by the corresponding error bound. We provide numerical results that corroborate the theoretical finding. Importantly, SGD not only converges faster in run time with fewer observations than alternating minimization and GD in the noiseless scenario but also outperforms them in low-sample scenarios with noise.

stat.ML↗

arXiv2023

Sketching low-rank matrices with a shared column space by convex programming

In many practical applications including remote sensing, multi-task learning, and multi-spectrum imaging, data are described as a set of matrices sharing a common column space. We consider the joint estimation of such matrices from their noisy linear measurements. We study a convex estimator regularized by a pair of matrix norms. The measurement model corresponds to block-wise sensing and the reconstruction is possible only when the total energy is well distributed over blocks. The first norm, which is the maximum-block-Frobenius norm, favors such a solution. This condition is analogous to the notion of low-spikiness in matrix completion or column-wise sensing. The second norm, which is a tensor norm on a pair of suitable Banach spaces, induces low-rankness in the solution together with the first norm. We demonstrate that the joint estimation provides a significant gain over the individual recovery of each matrix when the number of matrices sharing a column space and the ambient dimension of the shared column space are large relative to the number of columns in each matrix. The convex estimator is cast as a semidefinite program and an efficient ADMM algorithm is derived. The empirical behavior of the convex estimator is illustrated using Monte Carlo simulations and recovery performance is compared to existing methods in the literature.

math.ST↗

arXiv2021

Isotopic Compositions of Ruthenium Predicted from the NuGrid Project

The isotopic compositions of ruthenium (Ru) are measured from presolar silicon carbide (SiC) grains. In a popular scenario, the presolar SiC grains formed in the outskirt of an asymptotic giant branch (AGB) star, left the star as a stellar wind, and joined the presolar molecular cloud from which the solar system formed. The Ru isotopes formed inside the star, moved to the stellar surface during the AGB phase, and were locked into the SiC grains. Following this scenario, we analyze the NuGrid data which provide the abundances of the Ru isotopes in the stellar wind for a set of stars in a wide range of initial masses and metallicities. We apply the C>O (carbon abundance larger than the oxygen abundance) condition which is commonly adopted for the condition of the SiC formation in the stellar wind. The NuGrid data confirm that SiC grains do not form in the winds of massive stars. The isotopic compositions of Ru in the winds of low-mass stars can explain measurements. We find that lower-mass stars ($1.65~M_\odot$ and $2~M_\odot$) with low metallicity (Z=0.0001) can explain most of the measured isotopic compositions of Ru. We confirm that the abundance of ${^{99}}$Ru inside the presolar grain includes the contribution from the in-situ decay of ${^{99}}$Tc. We also verify our conclusion by comparing the isotopic compositions of Ru integrated over all the pulses with those calculated at individual pulses.

astro-ph.SR↗

arXiv2021

Max-Linear Regression by Convex Programming

We consider the multivariate max-linear regression problem where the model parameters $\boldsymbol{\beta}_{1},\dotsc,\boldsymbol{\beta}_{k}\in\mathbb{R}^{p}$ need to be estimated from $n$ independent samples of the (noisy) observations $y = \max_{1\leq j \leq k} \boldsymbol{\beta}_{j}^{\mathsf{T}} \boldsymbol{x} + \mathrm{noise}$. The max-linear model vastly generalizes the conventional linear model, and it can approximate any convex function to an arbitrary accuracy when the number of linear models $k$ is large enough. However, the inherent nonlinearity of the max-linear model renders the estimation of the regression parameters computationally challenging. Particularly, no estimator based on convex programming is known in the literature. We formulate and analyze a scalable convex program given by anchored regression (AR) as the estimator for the max-linear regression problem. Under the standard Gaussian observation setting, we present a non-asymptotic performance guarantee showing that the convex program recovers the parameters with high probability. When the $k$ linear components are equally likely to achieve the maximum, our result shows a sufficient number of noise-free observations for exact recovery scales as {$k^{4}p$} up to a logarithmic factor. { This sample complexity coincides with that by alternating minimization (Ghosh et al., {2021}). Moreover, the same sample complexity applies when the observations are corrupted with arbitrary deterministic noise. We provide empirical results that show that our method performs as our theoretical result predicts, and is competitive with the alternating minimization algorithm particularly in presence of multiplicative Bernoulli noise. Furthermore, we also show empirically that a recursive application of AR can significantly improve the estimation accuracy.}

stat.ML↗

arXiv2019

Semi-Supervised Learning Detector for MU-MIMO Systems with One-bit ADCs

We study an uplink multiuser multiple-input multiple-output (MU-MIMO) system with one-bit analog-to-digital converters (ADCs). For such system, a supervised-learning (SL) detector has been recently proposed by modeling a non-linear end-to-end system function into a parameterized Bernoulli-like model. Despite its attractive performance, the SL detector requires a large amount of labeled data (i.e., pilot signals) to estimate the parameters of the underlying model accurately. This is because the amount of the parameters grows exponentially with the number of users. To overcome this drawback, we propose a semi-supervised learning (SSL) detector where both pilot signals (i.e., labeled data) and some part of data signals (i.e., unlabeled data) are used to estimate the parameters via expectation-maximization (EM) algorithm. Via simulation results, we demonstrate that the proposed SSL detector can achieve the performance of the existing SL detector with significantly lower pilot-overhead.

cs.IT↗

arXiv2018

A Supervised-Learning Detector for Multihop Distributed Reception Systems

We consider a multihop distributed uplink reception system in which $K$ users transmit independent messages to one data center of $N_{\rm r} \geq K$ receive antennas, with the aid of multihop intermediate relays. In particular, each antenna of the data center is equipped with one-bit analog-to-digital converts (ADCs) for the sake of power-efficiency. In this system, it is extremely challenging to develop a low-complexity detector due to the non-linearity of an end-to-end channel transfer function (created by relays' operations and one-bit ADCs). Furthermore, there is no efficient way to estimate such complex function with a limited number of training data. Motivated by this, we propose a supervised-learning (SL) detector by introducing a novel Bernoulli-like model in which training data is directly used to design a detector rather than estimating a channel transfer function. It is shown that the proposed SL detector outperforms the existing SL detectors based on Gaussian model for one-bit quantized (binary observation) systems. Furthermore, we significantly reduce the complexity of the proposed SL detector using the fast kNN algorithm. Simulation results demonstrate that the proposed SL detector can yield an attractive performance with a significantly lower complexity.

cs.IT↗

arXiv2017

Successive Cancellation Soft Output Detector For Uplink MU-MIMO Systems With One-bit ADCs

In this paper, we present a successive-cancellation-soft-output (SCSO) detector for an uplink multiuser multiple-input-multiple-output (MU-MIMO) system with one-bit analog-to-digital converters (ADCs). The proposed detector produces soft outputs (e.g., log-likelihood ratios (LLRs)) from one-bit quantized observations in a successive way: each user k's message is sequentially decoded from a channel decoder $k$ for $k=1,...,K$ in that order, and the previously decoded messages are exploited to improve the reliabilities of LLRs. Furthermore, we develop an efficient greedy algorithm to optimize a decoding order. Via simulation results, we demonstrate that the proposed ordered SCSO detector outperforms the other detectors for the coded MU-MIMO systems with one-bit ADCs.

cs.IT↗

arXiv2017

Uplink Multiuser Massive MIMO Systems with Low-Resolution ADCs: A Coding-Theoretic Approach

This paper considers an uplink multiuser massive multiple-input-multiple-output (MIMO) system with low-resolution analog-to-digital converters (ADCs), in which K users with a single-antenna communicate with one base station (BS) with Nr antennas. In this system, we present a novel multiuser MIMO detection framework that is inspired by coding theory. The key idea of the proposed framework is to create a code C of length 2Nr over a spatial domain. This code is constructed by a so-called auto-encoding function that is not designable but is completely described by a channel transformation followed by a quantization function of the ADCs. From this point of view, we convert a multiuser MIMO detection problem into an equivalent channel coding problem, in which a codeword of C corresponding to users' messages is sent over 2Nr parallel channels, each with different channel reliability. To the resulting problem, we propose a novel weighted minimum distance decoding (wMDD) that appropriately exploits the unequal channel reliabilities. It is shown that the proposed wMDD yields a non-trivial gain over the conventional minimum distance decoding (MDD). From coding-theoretic viewpoint, we identify that bit-error-rate (BER) exponentially decreases with the minimum distance of the code C, which plays a similar role with a condition number in conventional MIMO systems. Furthermore, we develop the communication method that uses the wMDD for practical scenarios where the BS has no knowledge of channel state information. Finally, numerical results are provided to verify the superiority of the proposed method.

cs.IT↗

arXiv2017

Uplink Multiuser Massive MIMO Systems with One-Bit ADCs: A Coding-Theoretic Viewpoint

This paper investigates an uplink multiuser massive multiple-input multiple-output (MIMO) system with one-bit analog-to-digital converters (ADCs), in which $K$ users with a single-antenna communicate with one base station (BS) with $n_r$ antennas. In this system, we propose a novel MIMO detection framework, which is inspired by coding theory. The key idea of the proposed framework is to create a non-linear code $\Cc$ of length $n_r$ and rate $K/n_r$ using the encoding function that is completely characterized by a non-linear MIMO channel matrix. From this, a multiuser MIMO detection problem is converted into an equivalent channel coding problem, in which a codeword of the $\Cc$ is sent over $n_r$ parallel binary symmetric channels, each with different crossover probabilities. Levereging this framework, we develop a maximum likelihood decoding method, and show that the minimum distance of the $\Cc$ is strongly related to a diversity order. Furthermore, we propose a practical implementation method of the proposed framework when the channel state information is not known to the BS. The proposed method is to estimate the code $\Cc$ at the BS using a training sequence. Then, the proposed {\em weighted} minimum distance decoding is applied. Simulations results show that the proposed method almost achieves an ideal performance with a reasonable training overhead.

cs.IT↗