arXiv subjects

Mehmet Can Yavuz

Publications and source records attributed to Mehmet Can Yavuz.

11 recordsLinked to original sources

arXiv2025

Multivariate Variational Autoencoder

Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian posterior, which simplifies optimization but rules out correlated uncertainty and often yields entangled or redundant latent dimensions. We introduce the Multivariate Variational Autoencoder (MVAE), a tractable full-covariance extension of the VAE that augments the encoder with sample-specific diagonal scales and a global coupling matrix. This induces a multivariate Gaussian posterior of the form $N(μ_ϕ(x), C \operatorname{diag}(σ_ϕ^2(x)) C^\top)$, enabling correlated latent factors while preserving a closed-form KL divergence and a simple reparameterization path. Beyond likelihood, we propose a multi-criterion evaluation protocol that jointly assesses reconstruction quality (MSE, ELBO), downstream discrimination (linear probes), probabilistic calibration (NLL, Brier, ECE), and unsupervised structure (NMI, ARI). Across Larochelle-style MNIST variants, Fashion-MNIST, and CIFAR-10/100, MVAE consistently matches or outperforms diagonal-covariance VAEs of comparable capacity, with particularly notable gains in calibration and clustering metrics at both low and high latent dimensions. Qualitative analyses further show smoother, more semantically coherent latent traversals and sharper reconstructions. All code, dataset splits, and evaluation utilities are released to facilitate reproducible comparison and future extensions of multivariate posterior models.

cs.LG↗

arXiv2025

Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix

A central challenge in representation learning is constructing latent embeddings that are both expressive and efficient. In practice, deep networks often produce redundant latent spaces where multiple coordinates encode overlapping information, reducing effective capacity and hindering generalization. Standard metrics such as accuracy or reconstruction loss provide only indirect evidence of such redundancy and cannot isolate it as a failure mode. We introduce a redundancy index, denoted rho(C), that directly quantifies inter-dimensional dependencies by analyzing coupling matrices derived from latent representations and comparing their off-diagonal statistics against a normal distribution via energy distance. The result is a compact, interpretable, and statistically grounded measure of representational quality. We validate rho(C) across discriminative and generative settings on MNIST variants, Fashion-MNIST, CIFAR-10, and CIFAR-100, spanning multiple architectures and hyperparameter optimization strategies. Empirically, low rho(C) reliably predicts high classification accuracy or low reconstruction error, while elevated redundancy is associated with performance collapse. Estimator reliability grows with latent dimension, yielding natural lower bounds for reliable analysis. We further show that Tree-structured Parzen Estimators (TPE) preferentially explore low-rho regions, suggesting that rho(C) can guide neural architecture search and serve as a redundancy-aware regularization target. By exposing redundancy as a universal bottleneck across models and tasks, rho(C) offers both a theoretical lens and a practical tool for evaluating and improving the efficiency of learned representations.

cs.LG↗

arXiv2025

Geopolitical Parallax: Beyond Walter Lippmann Just After Large Language Models

Objectivity in journalism has long been contested, oscillating between ideals of neutral, fact-based reporting and the inevitability of subjective framing. With the advent of large language models (LLMs), these tensions are now mediated by algorithmic systems whose training data and design choices may themselves embed cultural or ideological biases. This study investigates geopolitical parallax-systematic divergence in news quality and subjectivity assessments-by comparing article-level embeddings from Chinese-origin (Qwen, BGE, Jina) and Western-origin (Snowflake, Granite) model families. We evaluate both on a human-annotated news quality benchmark spanning fifteen stylistic, informational, and affective dimensions, and on parallel corpora covering politically sensitive topics, including Palestine and reciprocal China-United States coverage. Using logistic regression probes and matched-topic evaluation, we quantify per-metric differences in predicted positive-class probabilities between model families. Our findings reveal consistent, non-random divergences aligned with model origin. In Palestine-related coverage, Western models assign higher subjectivity and positive emotion scores, while Chinese models emphasize novelty and descriptiveness. Cross-topic analysis shows asymmetries in structural quality metrics Chinese-on-US scoring notably lower in fluency, conciseness, technicality, and overall quality-contrasted by higher negative emotion scores. These patterns align with media bias theory and our distinction between semantic, emotional, and relational subjectivity, and extend LLM bias literature by showing that geopolitical framing effects persist in downstream quality assessment tasks. We conclude that LLM-based media evaluation pipelines require cultural calibration to avoid conflating content differences with model-induced bias.

cs.CY↗

arXiv2025

RadGPT: Constructing 3D Image-Text Tumor Datasets

Cancers identified in CT scans are usually accompanied by detailed radiology reports, but publicly available CT datasets often lack these essential reports. This absence limits their usefulness for developing accurate report generation AI. To address this gap, we present AbdomenAtlas 3.0, the first public, high-quality abdominal CT dataset with detailed, expert-reviewed radiology reports. All reports are paired with per-voxel masks and they describe liver, kidney and pancreatic tumors. AbdomenAtlas 3.0 has 9,262 triplets of CT, mask and report--3,955 with tumors. These CT scans come from 17 public datasets. Besides creating the reports for these datasets, we expanded their number of tumor masks by 4.2x, identifying 3,011 new tumor cases. Notably, the reports in AbdomenAtlas 3.0 are more standardized, and generated faster than traditional human-made reports. They provide details like tumor size, location, attenuation and surgical resectability. These reports were created by 12 board-certified radiologists using our proposed RadGPT, a novel framework that converted radiologist-revised tumor segmentation masks into structured and narrative reports. Besides being a dataset creation tool, RadGPT can also become a fully-automatic, segmentation-assisted report generation method. We benchmarked this method and 5 state-of-the-art report generation vision-language models. Our results show that segmentation strongly improves tumor detection in AI-made reports.

eess.IV↗

arXiv2025

Variational Self-Supervised Learning

We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on input reconstruction via a decoder, VSSL symmetrically couples two encoders with Gaussian outputs. A momentum-updated teacher network defines a dynamic, data-dependent prior, while the student encoder produces an approximate posterior from augmented views. The reconstruction term in the ELBO is replaced with a cross-view denoising objective, preserving the analytical tractability of Gaussian KL divergence. We further introduce cosine-based formulations of KL and log-likelihood terms to enhance semantic alignment in high-dimensional latent spaces. Experiments on CIFAR-10, CIFAR-100, and ImageNet-100 show that VSSL achieves competitive or superior performance to leading self-supervised methods, including BYOL and MoCo V3. VSSL offers a scalable, probabilistically grounded approach to learning transferable representations without generative reconstruction, bridging the gap between variational modeling and modern self-supervised techniques.

cs.LG↗

arXiv2025

Policy Gradient-Driven Noise Mask

Deep learning classifiers face significant challenges when dealing with heterogeneous multi-modal and multi-organ biomedical datasets. The low-level feature distinguishability limited to imaging-modality hinders the classifiers' ability to learn high-level semantic relationships, resulting in sub-optimal performance. To address this issue, image augmentation strategies are employed as regularization techniques. While additive noise input during network training is a well-established augmentation as regularization method, modern pipelines often favor more robust techniques such as dropout and weight decay. This preference stems from the observation that combining these established techniques with noise input can adversely affect model performance. In this study, we propose a novel pretraining pipeline that learns to generate conditional noise mask specifically tailored to improve performance on multi-modal and multi-organ datasets. As a reinforcement learning algorithm, our approach employs a dual-component system comprising a very light-weight policy network that learns to sample conditional noise using a differentiable beta distribution as well as a classifier network. The policy network is trained using the reinforce algorithm to generate image-specific noise masks that regularize the classifier during pretraining. A key aspect is that the policy network's role is limited to obtaining an intermediate (or heated) model before fine-tuning. During inference, the policy network is omitted, allowing direct comparison between the baseline and noise-regularized models. We conducted experiments and related analyses on RadImageNet datasets. Results demonstrate that fine-tuning the intermediate models consistently outperforms conventional training algorithms on both classification and generalization to unseen concept tasks. https://github.com/convergedmachine/Policy-Gradient-Driven-Noise-Mask

eess.IV↗

arXiv2025

Cross-D Conv: Cross-Dimensional Transferable Knowledge Base via Fourier Shifting Operation

In biomedical imaging analysis, the dichotomy between 2D and 3D data presents a significant challenge. While 3D volumes offer superior real-world applicability, they are less available for each modality and not easy to train in large scale, whereas 2D samples are abundant but less comprehensive. This paper introduces Cross-D Conv operation, a novel approach that bridges the dimensional gap by learning the phase shifting in the Fourier domain. Our method enables seamless weight transfer between 2D and 3D convolution operations, effectively facilitating cross-dimensional learning. The proposed architecture leverages the abundance of 2D training data to enhance 3D model performance, offering a practical solution to the multimodal data scarcity challenge in 3D medical model pretraining. Experimental validation on the RadImagenet (2D) and multimodal volumetric sets demonstrates that our approach achieves comparable or superior performance in feature quality assessment. The enhanced convolution operation presents new opportunities for developing efficient classification and segmentation models in medical imaging. This work represents an advancement in cross-dimensional and multimodal medical image analysis, offering a robust framework for utilizing 2D priors in 3D model pretraining while maintaining computational efficiency of 2D training. The code is available on https://github.com/convergedmachine/Cross-D-Conv.

cs.CV↗

arXiv2024

Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography

The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often struggle with flexibility for partially annotated datasets and extensibility for new classes due to limitations in the one-hot encoding, architectural design, and learning scheme. To overcome these limitations, we propose a universal, extensible framework enabling a single model, termed Universal Model, to deal with multiple public datasets and adapt to new classes (e.g., organs/tumors). Firstly, we introduce a novel language-driven parameter generator that leverages language embeddings from large language models, enriching semantic encoding compared with one-hot encoding. Secondly, the conventional output layers are replaced with lightweight, class-specific heads, allowing Universal Model to simultaneously segment 25 organs and six types of tumors and ease the addition of new classes. We train our Universal Model on 3,410 CT volumes assembled from 14 publicly available datasets and then test it on 6,173 CT volumes from four external datasets. Universal Model achieves first place on six CT tasks in the Medical Segmentation Decathlon (MSD) public leaderboard and leading performance on the Beyond The Cranial Vault (BTCV) dataset. In summary, Universal Model exhibits remarkable computational efficiency (6x faster than other dataset-specific models), demonstrates strong generalization across different hospitals, transfers well to numerous downstream tasks, and more importantly, facilitates the extensibility to new classes while alleviating the catastrophic forgetting of previously learned classes. Codes, models, and datasets are available at https://github.com/ljwztc/CLIP-Driven-Universal-Model

eess.IV↗

arXiv2024

Variational Self-Supervised Contrastive Learning Using Beta Divergence

Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of variational methods. The method (VCL) utilizes variational contrastive learning with beta-divergence to learn robustly from unlabelled datasets, including uncurated and noisy datasets. We demonstrate the effectiveness of the proposed method through rigorous experiments including linear evaluation and fine-tuning scenarios with multi-label datasets in the face understanding domain. In almost all tested scenarios, VCL surpasses the performance of state-of-the-art self-supervised methods, achieving a noteworthy increase in accuracy.

cs.CV↗

arXiv2021

COVID-19 Detection in Computed Tomography Images with 2D and 3D Approaches

Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the definitive RT-PCR test. We present a deep learning ensemble for detecting COVID-19 infection, combining slice-based (2D) and volume-based (3D) approaches. The 2D system detects the infection on each CT slice independently, combining them to obtain the patient-level decision via different methods (averaging and long-short term memory networks). The 3D system takes the whole CT volume to arrive to the patient-level decision in one step. A new high resolution chest CT scan dataset, called the IST-C dataset, is also collected in this work. The proposed ensemble, called IST-CovNet, obtains 90.80% accuracy and 0.95 AUC score overall on the IST-C dataset in detecting COVID-19 among normal controls and other types of lung pathologies; and 93.69% accuracy and 0.99 AUC score on the publicly available MosMed dataset that consists of COVID-19 scans and normal controls only. The system is deployed at Istanbul University Cerrahpasa School of Medicine.

eess.IV↗

arXiv2021

Multilingual, Temporal and Sentimental Distant-Reading of City Events

Leibniz's Monadology mentions perceptional and sentimental variations of the individual in the city. It is the interaction of people with people and events. Film festivals are highly sentimental events of multicultural cities. Each movie has a different sentimental effect and the interactions with the movies have reflections that can be observed on social media. This analysis aims to apply distant reading on Berlinale tweets collected during the festival. On contrary to close reading, distant reading let authors to observe patterns in large collection of data. The analysis is temporal and sentimental in multilingual domain and strongly positive and negative time intervals are analysed. For this purpose, we trained a deep sentiment network with multilingual embeddings. These multilingual embeddings are aligned in latent space. We trained the network with a multilingual dataset in three languages English, German and Spanish. The trained algorithm has a 0.78 test score and applied on Tweets with Berlinale hashtag during the festival. Although the sentimental analysis does not reflect the award-winning films, we observe weekly routine on the relationship between sentimentality, which can mislead a close reading analysis. We have also remarks on popularity of the director or actors.

cs.CY↗