The paper introduces MOVAL, a model evaluation tool that estimates performance of deep neural networks on unlabeled test data by calibrating class-wise confidence scores. MOVAL mitigates issues from distributional shifts and class imbalance, enabling estimation of metrics beyond accuracy such as F1-Score and AUC. Experiments on natural and medical image datasets demonstrate state‑of‑the‑art results across classification and segmentation tasks, providing accurate class, instance, and pixel‑level performance estimates for safe deployment.
The main challenge in applying deep neural networks to real-world scenarios lies in distributional discrepancies between training and test datasets, often caused by variations in data acquisition cond...
arXiv:2610.03142v1 Announce Type: new Abstract: Deep neural networks remain vulnerable to adversarial perturbations, which can distort not only predictions but also confidence scores, undermining unc...
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
arXiv:2601. 07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge.
arXiv:2512. 21414v2 Announce Type: replace-cross Abstract: Recent tool-use frameworks powered by vision-language models (VLMs) improve image understanding by grounding model predictions with specialized tools.
arXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, eithe...
arXiv:2608. 12100v1 Announce Type: cross Abstract: In high-stakes applications, reliable confidence estimates are as important as the predictions themselves.
arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.
arXiv:2609.25850v1 Announce Type: new Abstract: Deep learning performance generally improves with increasing training data, yet this scaling is fundamentally constrained by annotation cost in large-s...
arXiv:2605. 09697v3 Announce Type: replace-cross Abstract: In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a severe scarcity of positive samples.
arXiv:2607. 22139v1 Announce Type: cross Abstract: Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols.
TestifAI is a deep learning testing framework that estimates model robustness against combinations of input perturbations efficiently. It allows users to define structured spaces of semantic perturbations and severity levels, then query robustness for any combination. By using partial model tomography, TestifAI reconstructs higher-order perturbation effects from low-order tests, achieving less than 7% error while reducing inferences by 60–80%.