arXiv subjects

Krishna Agarwal

Publications and source records attributed to Krishna Agarwal.

At least 19 recordsLinked to original sources

arXiv2026

SAM for Robust Mitochondria Instance Segmentation in Fluorescence Microscopy

The morphological analysis of mitochondria in fluorescence microscopy (FM) is crucial for understanding cellular health, energy production, and metabolic regulation. While foundation models like the Segment Anything Model (SAM) have revolutionized natural image segmentation, their direct application to FM is hindered by a significant domain shift characterized by diffraction-limited resolution, low contrast, and complex overlapping organelle networks. Furthermore, the development of robust models is bottlenecked by a severe lack of high-quality, manually annotated instance segmentation datasets for mitochondria. In this paper, we propose a scalable solution to this data scarcity by finetuning SAM exclusively on synthetically generated FM data. We simulate realistic mitochondria data and emulate the optical properties of fluorescence microscopes to create a large-scale annotated dataset. We evaluate our fine-tuned model on a curated dataset of real, manually annotated FM images. Qualitative and quantitative analyses demonstrate that our synthetically fine-tuned model improves precision and average dice score over strong baselines. This work establishes the potential of simulation-assisted training for FM instance segmentation.

cs.CV↗

arXiv2026

BShare: Packet Queueing Delay-Driven Buffer Sharing for Datacenter Switches

Modern datacenter switches share packet buffers across ports to boost overall throughput and reduce packet loss. However, as buffer availability per-port-per-bandwidth unit continues to decrease, existing buffer-sharing strategies face increasing performance challenges. Recent efforts have attempted to integrate Buffer Management (BM) with Active Queue Management (AQM) to harness the advantages of both BM and AQM approaches to improve performance. While these hybrid solutions show promise, their complexity of dynamically calculating multiple factors for integration hinders generalization and efficiency. This paper presents BShare, a simple buffer sharing mechanism that uses packet queueing delay. BShare requires only a single operator-configurable parameter. Our simulation results show that BSHARE improves the flow completion time (FCT) performance of advanced transport protocols, such as PowerTCP, by up to 45.07% compared to ABM, particularly under burst-heavy datacenter workloads.

cs.NI↗

arXiv2026

Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational Perspective

Small Language Models (SLMs) offer privacy and efficiency for educational deployment, yet their utility depends on reliable multistep reasoning. Existing benchmarks often prioritize final answer accuracy, obscuring 'right answer, wrong procedure' failures that can reinforce student misconceptions. This work investigates SLM physics reasoning reliability, stage wise failure modes, and robustness under paired contextual variants. We introduce Physbench, comprising of 3,162 high school and AP level physics questions derived from OpenStax in a structured reference solution format with Bloom's Taxonomy annotations, plus 2,700 paired culturally contextualized variants. Using P-REFS, a stage wise evaluation rubric, we assess 10 SLMs across 58,000 responses. Results reveal substantial reliability gap: among final answer correct solutions, 75 to 98% contain at least one reasoning error. Failure modes shift with model capability; weaker models fail primarily at interpretation or modeling while stronger models often fail during execution. Paired contextual variations have minimal impact on top models but degrade the performance of mid-tier models. These findings demonstrate that safe educational AI requires evaluation paradigms that prioritize reasoning fidelity over final-answer correctness.

cs.CL↗

arXiv2025

Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations

In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here, we assess the robustness of RPI's empirical performance on two classical control tasks -- CartPole and Inverted Pendulum -- under changes to neural network and environmental parameters. Relative to DQN, Double DQN, DDPG, TD3, and PPO, RPI reaches near-optimal performance early and sustains this policy as training proceeds. Because deep RL methods are often hampered by sample inefficiency, training instability, and hyperparameter sensitivity, our results highlight RPI's promise as a more reliable alternative.

cs.AI↗

arXiv2025

Haphazard Inputs as Images in Online Learning

The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages.

cs.CV↗

arXiv2024

packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space

We study the online learning problem characterized by the varying input feature space of streaming data. Although LSTMs have been employed to effectively capture the temporal nature of streaming data, they cannot handle the dimension-varying streams in an online learning setting. Therefore, we propose a dynamic LSTM-based novel method, called packetLSTM, to model the dimension-varying streams. The packetLSTM's dynamic framework consists of an evolving packet of LSTMs, each dedicated to processing one input feature. Each LSTM retains the local information of its corresponding feature, while a shared common memory consolidates global information. This configuration facilitates continuous learning and mitigates the issue of forgetting, even when certain features are absent for extended time periods. The idea of utilizing one LSTM per feature coupled with a dimension-invariant operator for information aggregation enhances the dynamic nature of packetLSTM. This dynamic nature is evidenced by the model's ability to activate, deactivate, and add new LSTMs as required, thus seamlessly accommodating varying input dimensions. The packetLSTM achieves state-of-the-art results on five datasets, and its underlying principle is extended to other RNN types, like GRU and vanilla RNN.

cs.LG↗

arXiv2024

Label-free correlative morpho-chemical tomography of 3D kidney mesangial cells

Label-free characterization of biological specimens seeks to supplement existing imaging techniques and avoid the need for contrast agents that can disturb the native state of living samples. Conventional label-free optical imaging techniques are compatible with living samples but face challenges such as poor sectioning capability, fragmentary morphology, and lack chemical specific information. Here, we combined simultaneous label-free autofluorescence multi-harmonic (SLAM) microscopy and gradient light interference microscopy (GLIM) to extract both chemical specific and morphological tomography of 3D cultured kidney mesangial cells. Imaging 3D in vitro kidney models is essential to understand kidney function and pathology. Our correlative approach enables imaging and quantification of these cells to extract both morphology and chemical-specific signals that is crucial for understanding kidney function. In our approach, SLAM offers a nonlinear imaging platform with a single-excitation source to simultaneously acquire autofluorescence (FAD and NAD(P)H), second, and third harmonic signal from the 3D cultured cells. Complementarily, GLIM acquires high-contrast quantitative phase information to quantify structural changes in samples with thickness of up to 250 micron. Our correlative imaging results demonstrate a versatile and hassle-free platform for morpho-chemical cellular tomography to investigate functions such as metabolism and matrix deposition of kidney mesangial cells in 3D under controlled physiological conditions.

physics.optics↗

arXiv2024

Online Learning under Haphazard Input Conditions: A Comprehensive Review and Analysis

The domain of online learning has experienced multifaceted expansion owing to its prevalence in real-life applications. Nonetheless, this progression operates under the assumption that the input feature space of the streaming data remains constant. In this survey paper, we address the topic of online learning in the context of haphazard inputs, explicitly foregoing such an assumption. We discuss, classify, evaluate, and compare the methodologies that are adept at modeling haphazard inputs, additionally providing the corresponding code implementations and their carbon footprint. Moreover, we classify the datasets related to the field of haphazard inputs and introduce evaluation metrics specifically designed for datasets exhibiting imbalance. The code of each methodology can be found at https://github.com/Rohit102497/HaphazardInputsReview

cs.LG↗

arXiv2023

Taxonomy of hybridly polarized Stokes vortex beams

Structured beams carrying topological defects, namely phase and Stokes singularities, have gained extensive interest in numerous areas of optics. The non-separable spin and orbital angular momentum states of hybridly polarized Stokes singular beams provide additional freedom for manipulating optical fields. However, the characterization of hybridly polarized Stokes vortex beams remains challenging owing to the degeneracy associated with the complex polarization structures of these beams. In addition, experimental noise factors such as relative phase, amplitude, and polarization difference together with beam fluctuations add to the perplexity in the identification process. Here, we present a generalized diffraction-based Stokes polarimetry approach assisted with deep learning for efficient identification of Stokes singular beams. A total of 15 classes of beams are considered based on the type of Stokes singularity and their associated mode indices. The resultant total and polarization component intensities of Stokes singular beams after diffraction through a triangular aperture are exploited by the deep neural network to recognize these beams. Our approach presents a classification accuracy of 98.67% for 15 types of Stokes singular beams that comprise several degenerate cases. The present study illustrates the potential of diffraction of the Stokes singular beam with polarization transformation, modeling of experimental noise factors, and a deep learning framework for characterizing hybridly polarized beams

physics.optics↗

arXiv2023

MiShape: 3D Shape Modelling of Mitochondria in Microscopy

Fluorescence microscopy is a quintessential tool for observing cells and understanding the underlying mechanisms of life-sustaining processes of all living organisms. The problem of extracting 3D shape of mitochondria from fluorescence microscopy images remains unsolved due to the complex and varied shapes expressed by mitochondria and the poor resolving capacity of these microscopes. We propose an approach to bridge this gap by learning a shape prior for mitochondria termed as MiShape, by leveraging high-resolution electron microscopy data. MiShape is a generative model learned using implicit representations of mitochondrial shapes. It provides a shape distribution that can be used to generate infinite realistic mitochondrial shapes. We demonstrate the representation power of MiShape and its utility for 3D shape reconstruction given a single 2D fluorescence image or a small 3D stack of 2D slices. We also showcase applications of our method by deriving simulated fluorescence microscope datasets that have realistic 3D ground truths for the problem of 2D segmentation and microscope-to-microscope transformation.

eess.IV↗

arXiv2022

High-performance computing for super-resolution microscopy on a cluster of computers

Multiple signal classification algorithm (MUSICAL) provides a super-resolution microscopy method. In the previous research, MUSICAL has enabled data-parallelism well on a desktop computer or a Linux-based server. However, the running time needs to be shorter. This paper will develop a new parallel MUSICAL with high efficiency and scalability on a cluster of computers. We achieve the purpose by using the optimal speed of the cluster cores, the latest parallel programming techniques, and the high-performance computing libraries, such as the Intel Threading Building Blocks (TBB), the Intel Math Kernel Library (MKL), and the unified parallel C++ (UPC++) for the cluster of computers. Our experimental results show that the new parallel MUSICAL achieves a speed-up of 240.29x within 10 seconds on the 256-core cluster with an efficiency of 93.86%. Our MUSICAL offers a high possibility for real-life applications to make super-resolution microscopy within seconds.

cs.DC↗

arXiv2022

Label-free chip-based evanescent light scattering super-resolution and superior-contrast optical microscopy (cELS)

Chip-based Evanescent Light Scattering (cELS) utilizes the multiple modes of a high-index contrast optical waveguide for near-field illumination of unlabeled samples, thereby repositioning the highest spatial frequencies of the sample into the far-field. The multiple modes scattering off the sample with different phase differences is engineered to have random spatial distributions within the integration time of the camera, mitigating the coherent speckle noise. This enables label-free superior-contrast imaging of weakly scattering nanosized specimens such as extra-cellular vesicles (EVs) and liposomes, dynamics of living HeLa cells etc. The article explains and validates experimentally the physics behind cELS by demonstrating a multi-moded straight waveguide as a partially coherent light source. For isotropic super-resolution, spatially incoherent light engineered via multiple-arms waveguide chip and intensity-fluctuation based algorithms are used. The proof-of-concept results are demonstrated on 100 nm polystyrene beads and resolution improvement of close to 2X is shown. cELS also realizes (2-10)X more contrast as opposed to conventional imaging techniques. In addition, cELS platform is miniaturized and enables large field-of-view imaging compared to state of the art label-free techniques. cELS holds a potential for label-free super-resolution imaging of nanosized biological specimens at high-throughput.

physics.optics↗

arXiv2022

Single-shot multispectral quantitative phase imaging using deep neural network

Multi-spectral quantitative phase imaging (MS-QPI) is a cutting-edge label-free technique to determine the morphological changes, refractive index variations and spectroscopic information of the specimens. The bottleneck to implement this technique to extract quantitative information, is the need of more than two measurements for generating MS-QPI images. We propose a single-shot MS-QPI technique using highly spatially sensitive digital holographic microscope assisted with deep neural network (DNN). Our method first acquires the interferometric datasets corresponding to multiple wavelengths (λ=532, 633 and 808 nm used here). The acquired datasets are used to train generative adversarial network (GAN) to generate multi-spectral quantitative phase maps from a single input interferogram. The network is trained and validated on two different samples, the optical waveguide and a MG63 osteosarcoma cells. Further, validation of the framework is performed by comparing the predicted phase maps with experimentally acquired and processed multi-spectral phase maps. The current MS-QPI+DNN framework can further empower spectroscopic QPI to improve the chemical specificity without complex instrumentation and color-cross talk.

physics.optics↗

arXiv2021

Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering

Solving electromagnetic inverse scattering problems (ISPs) is challenging due to the intrinsic nonlinearity, ill-posedness, and expensive computational cost. Recently, deep neural network (DNN) techniques have been successfully applied on ISPs and shown potential of superior imaging over conventional methods. In this paper, we analyse the analogy between DNN solvers and traditional iterative algorithms and discuss how important physical phenomena cannot be effectively incorporated in the training process. We show the importance of including near-field priors in the learning process of DNNs. To this end, we propose new designs of loss functions which incorporate multiple-scattering based near-field quantities (such as scattered fields or induced currents within domain of interest). Effects of physics-guided loss functions are studied using a variety of numerical experiments. Pros and cons of the investigated ISP solvers with different loss functions are summarized.

cs.LG↗

arXiv2020

Artefact removal in ground truth and noise model deficient sub-cellular nanoscopy images using auto-encoder deep learning

Image denoising or artefact removal using deep learning is possible in the availability of supervised training dataset acquired in real experiments or synthesized using known noise models. Neither of the conditions can be fulfilled for nanoscopy (super-resolution optical microscopy) images that are generated from microscopy videos through statistical analysis techniques. Due to several physical constraints, supervised dataset cannot be measured. Due to non-linear spatio-temporal mixing of data and valuable statistics of fluctuations from fluorescent molecules which compete with noise statistics, noise or artefact models in nanoscopy images cannot be explicitly learnt. Therefore, such problem poses unprecedented challenges to deep learning. Here, we propose a robust and versatile simulation-supervised training approach of deep learning auto-encoder architectures for the highly challenging nanoscopy images of sub-cellular structures inside biological samples. We show the proof of concept for one nanoscopy method and investigate the scope of generalizability across structures, noise models, and nanoscopy algorithms not included during simulation-supervised training. We also investigate a variety of loss functions and learning models and discuss the limitation of existing performance metrics for nanoscopy images. We generate valuable insights for this highly challenging and unsolved problem in nanoscopy, and set the foundation for application of deep learning problems in nanoscopy for life sciences.

eess.IV↗

arXiv2020

Soft thresholding schemes for multiple signal classification algorithm

Multiple signal classification algorithm (MUSICAL) exploits temporal fluctuations in fluorescence intensity to perform super-resolution microscopy by computing the value of a super-resolving indicator function across a fine sample grid. A key step in the algorithm is the separation of the measurements into signal and noise subspaces, based on a single user-specified parameter called the threshold. The resulting image is strongly sensitive to this parameter and the subjectivity arising from multiple practical factors makes it difficult to determine the right rule of selection. We address this issue by proposing soft thresholding schemes derived from a new generalized framework for indicator function design. We show that the new schemes significantly alleviate the subjectivity and sensitivity of hard thresholding while retaining the super-resolution ability. We also evaluate the trade-off between resolution and contrast and the out-of-focus light rejection using the various indicator functions. Through this, we create significant new insights into the use and further optimization of MUSICAL for a wide range of practical scenarios.

eess.IV↗

arXiv2020

Auxiliary Network: Scalable and agile online learning for dynamic system with inconsistently available inputs

Streaming classification methods assume the number of input features is fixed and always received. But in many real-world scenarios demand is some input features are reliable while others are unreliable or inconsistent. In this paper, we propose a novel deep learning-based model called Auxiliary Network (Aux-Net), which is scalable and agile. It employs a weighted ensemble of classifiers to give a final outcome. The Aux-Net model is based on the hedging algorithm and online gradient descent. It employs a model of varying depth in an online setting using single pass learning. Aux-Net is a foundational work towards scalable neural network model for a dynamic complex environment requiring ad hoc or inconsistent input data. The efficacy of Aux-Net is shown on public dataset.

cs.LG↗

arXiv2020

Simulation-supervised deep learning for analysing organelles states and behaviour in living cells

In many real-world scientific problems, generating ground truth (GT) for supervised learning is almost impossible. The causes include limitations imposed by scientific instrument, physical phenomenon itself, or the complexity of modeling. Performing artificial intelligence (AI) tasks such as segmentation, tracking, and analytics of small sub-cellular structures such as mitochondria in microscopy videos of living cells is a prime example. The 3D blurring function of microscope, digital resolution from pixel size, optical resolution due to the character of light, noise characteristics, and complex 3D deformable shapes of mitochondria, all contribute to making this problem GT hard. Manual segmentation of 100s of mitochondria across 1000s of frames and then across many such videos is not only herculean but also physically inaccurate because of the instrument and phenomena imposed limitations. Unsupervised learning produces less than optimal results and accuracy is important if inferences relevant to therapy are to be derived. In order to solve this unsurmountable problem, we bring modeling and deep learning to a nexus. We show that accurate physics based modeling of microscopy data including all its limitations can be the solution for generating simulated training datasets for supervised learning. We show here that our simulation-supervised segmentation approach is a great enabler for studying mitochondrial states and behaviour in heart muscle cells, where mitochondria have a significant role to play in the health of the cells. We report unprecedented mean IoU score of 91% for binary segmentation (19% better than the best performing unsupervised approach) of mitochondria in actual microscopy videos of living cells. We further demonstrate the possibility of performing multi-class classification, tracking, and morphology associated analytics at the scale of individual mitochondrion.

eess.IV↗