{"id":495,"date":"2019-05-06T17:04:51","date_gmt":"2019-05-06T16:04:51","guid":{"rendered":"https:\/\/www.es.mdh.se\/hero\/?page_id=495"},"modified":"2026-03-26T08:47:33","modified_gmt":"2026-03-26T07:47:33","slug":"tools","status":"publish","type":"page","link":"https:\/\/www.es.mdu.se\/deephero\/tools\/","title":{"rendered":"Tools"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
<\/div>\n\t\t\t\t\t\t
\n\t\t\t\n\t\n<\/svg>\t\t<\/div>\n\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Training-Free Quantum Architecture Search under Realistic Noise via Expressibility-Guided Evolution<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Designing noise-robust parameterized quantum circuits (PQCs) is a central challenge in the noisy intermediate-scale quantum (NISQ) regime. Existing quantum architecture search methods rely on training large SuperCircuits and evaluating SubCircuits under noisy execution, resulting in high computational cost and architecture assessments that depend on task-specific optimization and device noise. In this work, we propose a training-free quantum architecture search framework based on information-theoretic expressibility measures rather than performance-based estimators. We empirically show that noise-free KL-divergence-based expressibility exhibits a consistent monotonic association with noisy task loss across diverse circuit architectures and realistic hardware noise models. Leveraging this relationship, we introduce an expressibility-guided evolutionary search that requires neither SuperCircuit training nor noisy execution during the search phase. Since expressibility is evaluated independently of hardware noise, the method is inherently device-agnostic, enabling architectures to be reused across multiple quantum devices without re-running the search. Experiments using IBM-derived Qiskit noise models demonstrate that the proposed approach achieves competitive performance compared to SuperCircuit-based baselines, while substantially reducing computational cost. These results establish expressibility as an effective information-theoretic surrogate for ranking PQC architectures under realistic~noise.\u00a0<\/span><\/p><\/div>

Paper link: https:\/\/www.mdpi.com\/1099-4300\/28\/3\/330<\/a><\/p>

Code: https:\/\/github.com\/s110m\/TF-QAS<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tMore info<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

FedLoRASwitch: Efficient Federated Learning via LoRA Expert Hotswapping and Routing<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

FedLoRASwitch is a framework that combines federated learning (FL)<\/b>, Low-Rank Adaptation (LoRA)<\/b>, and Mixture-of-Experts (MoE)<\/b> principles to enable the efficient and private adaptation of large language models (LLMs)<\/span>. <\/span>The tool operates by collaboratively training multiple domain-specific LoRA “experts” (such as for math or coding) across decentralized clients without sharing raw data<\/span>. <\/span>At inference time, a lightweight Transformer router<\/b> analyzes incoming queries to select the most relevant expert, which is then dynamically “hot-swapped” or merged with a frozen base model to generate a response<\/span>. <\/span>Experimental results show that this approach can provide substantial performance gains, such as an 8-fold increase in mathematical reasoning accuracy, while reducing communication overhead by approximately 40x compared to traditional full-parameter training.<\/span><\/p><\/div>

Paper: https:\/\/www.es.mdu.se\/pdf_publications\/7245.pdf<\/a><\/p>

Code: Will be shared later…<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tMore info<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

ProARD: Progressive Adversarial Robustness Distillation: Provide Wide Range of Robust Students<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The Progressive Adversarial Robustness Distillation (ProARD) approach efficiently trains a wide range of robust student networks within a single dynamic network by using a three-step progressive sampling strategy. This strategy progressively reduces the size of the sampled student networks over the course of the training. In the first step, the depth and expansion are fixed, and different student networks are extracted by varying only the width (or kernel size for MobileNet). In the second step, the expansion is fixed while both the width (or kernel size) and depth are varied to train the student networks. Finally, the third step extracts and trains student networks by varying all three configuration parameters: width (or kernel size), depth, and expansion. In each step, robustness distillation is applied between the dynamic teacher and the selected students, and the student parameters are shared with the dynamic teacher network.<\/p>

Paper: https:\/\/ieeexplore.ieee.org\/document\/11227836<\/a><\/p>

Code: https:\/\/github.com\/hamidmousavi0\/ProARD<\/a><\/p><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tMore info<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Frequency Domain Complex-Valued Convolutional Neural Network<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

This paper\u00a0presents a fully complex-valued residual CNN that operates entirely in the frequency domain to efficiently process complex data. Traditional real-valued CNNs lose important phase information and are computationally intensive, while prior complex-valued models depend heavily on FFT\/IFFT transformations and incomplete complex formulations. To address these issues, the authors design lightweight, fully complex building blocks\u2014including complex convolution, normalization, pooling, and a new Log-Magnitude activation function that preserves phase and stabilizes gradient flow. This model significantly reduces computational complexity while maintaining expressive power. Evaluated across multiple datasets (MNIST, SVHN, MIT-BIH Arrhythmia, PTB Diagnostic ECG, DIAT-\u03bcRadHAR, and DIAT-\u03bcSAT), the proposed approach outperforms both real-valued and existing hybrid complex-valued CNNs in accuracy, efficiency, and generalization, demonstrating the potential of frequency-domain complex-valued deep learning for diverse real-world applications.<\/p>

Paper: https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417425025102<\/a><\/p>

Code: https:\/\/github.com\/mainak15\/FDCVNNv0.0<\/a><\/p><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tMore info<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

HeRD: Modelling Heterogeneous Degradations for Federated Super-Resolution in Satellite Imagery<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

This work, “HeRD: Modeling Heterogeneous Degradations for Federated Super-Resolution in Satellite Imagery,” introduces a novel strategy for training super-resolution models on decentralized satellite data while preserving privacy. Traditional methods often fail to account for the unique and complex image degradations caused by different satellite hardware, creating a gap between training and real-world application. The HeRD (Heterogeneous Realistic Degradation) strategy addresses this by realistically simulating these diverse, client-specific degradations\u2014such as anisotropic blur and sensor noise\u2014directly on each local device. This allows for the collaborative training of a powerful, global super-resolution model using federated learning, where raw data never leaves the owner’s control. Our extensive experiments show that this approach is highly effective, achieving image quality that is nearly on par with models trained on a centralized dataset, even in highly heterogeneous environments. This makes HeRD a viable, high-performance, and privacy-first solution for enhancing satellite imagery where data sovereignty is critical.<\/p><\/div>

Paper:\u00a0https:\/\/ieeexplore.ieee.org\/abstract\/document\/11083581<\/a><\/p>

Code: https:\/\/github.com\/bostankhan6\/HeRD-Modelling-Heterogeneous-Degradations-for-Federated-Super-Resolution-in-Satellite-Imagery<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tMore info<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

SentinelNN: A Framework for Fault Resilience Assessment and Enhancement of CNNs<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
SentinelNN is a user-friendly, open-source framework to analyze and enhance the fault tolerance of CNN models for any DNN accelerator. SentinelNN provides a set of methods for the resilience analysis of channels against bitflips in convolutional layers, including DeepVigor, which is an accurate and scalable method for identifying the most vulnerable channels in CNNs.\u00a0<\/div>
\u00a0<\/div>
To mitigate the impact of faults, SentinelNN applies a user-specified selective channel duplication and hardening to detect and correct the faults during the inference. Furthermore, it leverages structural pruning to remove the least vulnerable channels to provide cost-effective fault-tolerance. The output of SentinelNN is a saved CNN model that can be conducted by any CNN accelerator.\u00a0<\/div>
\u00a0<\/div>
Paper:\u00a0https:\/\/ieeexplore.ieee.org\/document\/10616072<\/a><\/div>
Code:\u00a0https:\/\/github.com\/mhahmadilivany\/SentinelNN?tab=readme-ov-file<\/a><\/div>
\u00a0<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tMore info<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Contrastive Learning for Lane Detection via cross-similarity<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Contrastive Learning for Lane Detection via cross-similarity (CLLD), is a self-supervised learning method that tackles this challenge by enhancing lane detection models\u2019 resilience to real-world conditions that cause lane low visibility. CLLD is a novel multitask contrastive learning that trains lane detection approaches to detect lane markings even in low visible situations by integrating local feature contrastive learning (CL) with our new proposed operation cross-similarity. To ease of understanding some details are listed in the following:<\/p>