Signed pairwise interaction scores conflate U/R/S; Stochastic Hi-Fi uses interventional masked inference to recover per-feature uniqueness, redundancy, and synergy profiles.
super hub Mixed citations
Densely connected convolutional networks
Mixed citation behavior. Most common role is method (57%).
32
Pith papers citing it
44.7k
external citations · OpenAlex
Method
57% of classified citations
hub tools
citation-role summary
method 4
background 3
citation-polarity summary
representative citing papers
GPROF-IR is a CNN-based retrieval that uses temporal context in geostationary IR observations to produce precipitation estimates with lower error than prior IR methods and climatological consistency with PMW retrievals for integration into IMERG V08.
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
Presents a stochastic gradient algorithm for non-separable optimization with local convergence guarantees under smoothness assumptions.
UFPR-VeSV is a new real-world dataset for fine-grained vehicle classification and automatic license plate recognition collected from Brazilian police cameras, with benchmarks demonstrating its difficulty and the value of joint task use.
A reproducible pipeline produces physical adversarial traffic signs that successfully attack production-grade traffic sign recognition systems in a real car under black-box conditions.
A new multimodal fusion model using image, text, and clinical encoders with Transformer fusion reaches 77.64% accuracy on a pathology-confirmed 910-patient breast ultrasound dataset for distinguishing fibroadenoma from phyllodes tumors.
Finite-sample noise collapses the eigengap in representation covariances limiting recoverable modes K(N); multimodal learning stabilizes it via low-rank constraints, yielding better class separation quantified by truncated Mahalanobis energy approximated with a zeta function.
H-SemiS decomposes multi-class KOA severity grading into binary sub-tasks in a semi-supervised setup with self-supervision and quantum-inspired mixing, outperforming baselines on two multi-class and two binary datasets.
Proposes a multimodal model with cross-attention and missingness-aware dictionary learning for robust DICOM series classification that outperforms image-only, metadata-only, and other multimodal baselines on liver MRI datasets.
A CNN classifies lung cytology patches as benign or malignant at 100% sensitivity and 96.4% specificity, then routes to one of two Transformer decoders to generate findings text achieving BLEU-4 of 0.828 on 801 images.
A framework learns collection embeddings from runway images and applies RNN/LSTM to predict next-season designs at 78.42% average AUC over 32 years of data.
Presents a fully automated deep learning framework for pixel-wise segmentation of RPE loss, EZ loss, and EZ thinning in SD-OCT volumes for GA monitoring, validated on external data with high accuracy metrics.
MAPE combines a channel-attention U-Net (SAPE) trained on multi-model adversarial examples scheduled by PPSA to eliminate perturbations, reporting over 95.1% average defense on CIFAR-10 and 71.5% on Mini-ImageNet against black-box transferable attacks.
Zero-shot LLMs achieve near-chance ROC-AUC (~0.5) on ECG image classification while CNN models reach 0.92-0.94 internally and 0.85-0.86 externally on PTB-XL.
MIDOG 2025 challenge shows top mitosis detection F1 of 0.740 and atypical figure balanced accuracy of 0.908 across diverse tumors, with clear drops in challenging regions and tumor-type variation.
LGC performs curvature-aware geometric search in a compressed semantic manifold for decision-based attacks, using residual adversarial generation to reach SSIM >0.99 and LPIPS <0.01 at 5000 queries while attacking robust models.
HeartBeatAI reports 98% Macro F1 under intra-source testing on four ECG datasets but shows significant degradation on rare anomalies under leave-one-domain-out evaluation.
The study shows clinical AI accuracy collapsing from 89% to 62% on X-rays under imperceptible adversarial perturbations and from 85% to 55% on clinical cases in Nigerian Pidgin and Yoruba-inflected English.
A two-stage deep learning framework segments ten GI organs from coronal MR enterography images, achieving mean DSC of 88.99% and outperforming baselines.
A hybrid Swin Transformer and ResNet50 transfer learning model achieves up to 100% test accuracy on multi-type cancer histopathological image classification.
Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
The paper proposes the Aesthetic Multi-Attribute Network (AMAN) that jointly predicts captions and scores for five aesthetic attributes using a new weakly-labeled dataset created via knowledge transfer.
citing papers explorer
-
The Representational Limit of Scalar Interactions: An Interventional Decomposition
Signed pairwise interaction scores conflate U/R/S; Stochastic Hi-Fi uses interventional masked inference to recover per-feature uniqueness, redundancy, and synergy profiles.
-
GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products
GPROF-IR is a CNN-based retrieval that uses temporal context in geostationary IR observations to produce precipitation estimates with lower error than prior IR methods and climatological consistency with PMW retrievals for integration into IMERG V08.
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
A stochastic gradient algorithm for non-separable optimization with convergence guarantee
Presents a stochastic gradient algorithm for non-separable optimization with local convergence guarantees under smoothness assumptions.
-
Toward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition
UFPR-VeSV is a new real-world dataset for fine-grained vehicle classification and automatic license plate recognition collected from Brazilian police cameras, with benchmarks demonstrating its difficulty and the value of joint task use.
-
Fooling a Real Car with Adversarial Traffic Signs
A reproducible pipeline produces physical adversarial traffic signs that successfully attack production-grade traffic sign recognition systems in a real car under black-box conditions.
-
Multimodal Fusion for Fine-Grained Classification of Breast Fibroadenoma and Phyllodes Tumors
A new multimodal fusion model using image, text, and clinical encoders with Transformer fusion reaches 77.64% accuracy on a pathology-confirmed 910-patient breast ultrasound dataset for distinguishing fibroadenoma from phyllodes tumors.
-
Anchoring the Eigengap: Cross-Modal Spectral Stabilization for Sample-Efficient Representation Learning
Finite-sample noise collapses the eigengap in representation covariances limiting recoverable modes K(N); multimodal learning stabilizes it via low-rank constraints, yielding better class separation quantified by truncated Mahalanobis energy approximated with a zeta function.
-
H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Grading
H-SemiS decomposes multi-class KOA severity grading into binary sub-tasks in a semi-supervised setup with self-supervision and quantum-inspired mixing, outperforming baselines on two multi-class and two binary datasets.
-
Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning
Proposes a multimodal model with cross-attention and missingness-aware dictionary learning for robust DICOM series classification that outperforms image-only, metadata-only, and other multimodal baselines on liver MRI datasets.
-
Automated Description Generation of Cytologic Findings for Lung Cytological Images Using a Pretrained Vision Model and Dual Text Decoders: Preliminary Study
A CNN classifies lung cytology patches as benign or malignant at 100% sensitivity and 96.4% specificity, then routes to one of two Transformer decoders to generate findings text achieving BLEU-4 of 0.828 on 801 images.
-
Predicting Next-Season Designs on High Fashion Runway
A framework learns collection embeddings from runway images and applies RNN/LSTM to predict next-season designs at 78.42% average AUC over 32 years of data.
-
Fully Automated High-Precision Segmentation of Retinal Atrophy and Ellipsoid Zone Thickness in OCT: A Reliable Tool for Real-World GA Monitoring
Presents a fully automated deep learning framework for pixel-wise segmentation of RPE loss, EZ loss, and EZ thinning in SD-OCT volumes for GA monitoring, validated on external data with high accuracy metrics.
-
MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination
MAPE combines a channel-attention U-Net (SAPE) trained on multi-model adversarial examples scheduled by PPSA to eliminate perturbations, reporting over 95.1% average defense on CIFAR-10 and 71.5% on Mini-ImageNet against black-box transferable attacks.
-
Physiology-Aware CNN and Zero-Shot Multimodal LLMs for ECG Image Classification: A Comparative Study
Zero-shot LLMs achieve near-chance ROC-AUC (~0.5) on ECG image classification while CNN models reach 0.92-0.94 internally and 0.85-0.86 externally on PTB-XL.
-
Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge
MIDOG 2025 challenge shows top mitosis detection F1 of 0.740 and atypical figure balanced accuracy of 0.908 across diverse tumors, with clear drops in challenging regions and tumor-type variation.
-
Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
LGC performs curvature-aware geometric search in a compressed semantic manifold for decision-based attacks, using residual adversarial generation to reach SSIM >0.99 and LPIPS <0.01 at 5000 queries while attacking robust models.
-
HeartBeatAI: An Interpretable and Robust Deep Learning Framework for Multi-Label ECG Arrhythmia Detection
HeartBeatAI reports 98% Macro F1 under intra-source testing on four ECG datasets but shows significant degradation on rare anomalies under leave-one-domain-out evaluation.
-
Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings
The study shows clinical AI accuracy collapsing from 89% to 62% on X-rays under imperceptible adversarial perturbations and from 85% to 55% on clinical cases in Nigerian Pidgin and Yoruba-inflected English.
-
A Two-Stage Deep Learning Framework for Segmentation of Ten Gastrointestinal Organs from Coronal MR Enterography
A two-stage deep learning framework segments ten GI organs from coronal MR enterography images, achieving mean DSC of 88.99% and outperforming baselines.
-
DSVTLA: Deep Swin Vision Transformer-Based Transfer Learning Architecture for Multi-Type Cancer Histopathological Cancer Image Classification
A hybrid Swin Transformer and ResNet50 transfer learning model achieves up to 100% test accuracy on multi-type cancer histopathological image classification.
-
Safeguarding AI in Medical Imaging: Post-Hoc Out-of-Distribution Detection with Normalizing Flows
Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.
-
Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
-
Aesthetic Attributes Assessment of Images
The paper proposes the Aesthetic Multi-Attribute Network (AMAN) that jointly predicts captions and scores for five aesthetic attributes using a new weakly-labeled dataset created via knowledge transfer.
-
Cross-Architectural Mixture-of-Experts with Adaptive Soft Routing for Plant Leaf Disease Classification
A soft-gated MoE combining EfficientNet-B0, DenseNet-121, and Swin-Tiny reports 92.62% F1-score on an imbalanced potato leaf disease dataset, outperforming single models by 5%.
-
Digital Image Forgery Detection Using Transfer Learning
A hybrid RGB plus compression-feature transfer learning pipeline with Youden-optimized thresholds improves forgery detection on the CASIA v2.0 dataset using off-the-shelf CNN backbones.
-
Developing a Strong Pre-Trained Base Model for Plant Leaf Disease Classification
A DenseNet201 base model trained on a constructed plant leaf disease dataset outperforms baselines and enables faster, more robust transfer learning with less data than general models.
-
CNNs, Transformers, Hybrid, and Vision Language Models for Skin Cancer Detection
Benchmark of twelve models finds hybrid CNN-transformer architectures and a SigLIP vision-language model deliver the strongest overall performance on skin cancer detection using the PAD-UFES-20 dataset.
-
A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
Empirical comparison of transfer learning performance across eleven pre-trained models on five image datasets using accuracy, time, and size metrics.
-
Vision Language Models versus Machine Learning Models Performance on Polyp Detection and Classification in Colonoscopy Images
Empirical benchmark of 11 models on polyp detection and classification in colonoscopy images shows ResNet50 highest, BiomedCLIP and GPT-4 moderate on detection, and general VLMs weak on classification.
-
Deep Learning in the Automotive Industry: Recent Advances and Application Examples
An overview of deep learning applications and challenges in the automotive industry, covering ADAS, automated driving, virtual sensing, and data-driven development.
- NeuroBridge: Bridging Multi-Task MRI Knowledge for Neurodegenerative Disease Diagnosis