arXiv:2608. 14539v1 Announce Type: cross Abstract: Determining the biological sex of the individuals who created Upper Paleolithic hand stencils remains a challenging problem due to the absence of ground truth, population differences between contemporary and prehistoric groups, and the uncertainty introduced by image degradation.
arXiv:2607. 26743v1 Announce Type: cross Abstract: Artificial intelligence has shown considerable potential for archaeological applications, yet its use in zooarchaeology remains limited, particularly for the identification of avian skeletal remains.
arXiv:2608.30789v1 Announce Type: new Abstract: Supervised deep learning methods enable the rapid processing of ecological image data, but depend on a costly annotation process. Consequently, trainin...
arXiv:2606. 15837v1 Announce Type: cross Abstract: Deep neural networks (DNNs) frequently fail to generalize to out-of-distribution (OOD) medical images because of variations in scanners and acquisition protocols.
arXiv:2204. 14224v3 Announce Type: replace-cross Abstract: The automated analysis of heterogeneous natural textures is frequently hindered by physical damage and data loss, presenting a significant challenge to computer vision.
arXiv:2607. 16378v1 Announce Type: cross Abstract: Estimating the apparent age of individuals from facial images is challenging due to the subjective nature of perception and the inherent variability of the data.
The study investigates whether Vision Transformer (ViT)-based animal re-identification models learn biologically meaningful concepts. Using a DINOv3 backbone fine‑tuned on Western lowland gorilla images, the authors find that sex and age emerge as linear directions in the model’s representations, generalizing to unseen individuals with high AUROC scores. They demonstrate that the sex direction is causally used by the model, that fine‑tuning relocates these concepts within the network, and that the representations reflect a graded biological axis encoded redundantly across the population.
arXiv:2607. 28248v1 Announce Type: cross Abstract: The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification.
The paper examines whether model uncertainty aligns with human disagreement on vision tasks. Using multi‑annotator datasets (FER+ and CIFAR‑10H), the authors find that pretrained models rarely reflect the ambiguity humans perceive, with weak correlations between model confidence and human disagreement. Predictive multiplicity offers only modest improvement, indicating that common uncertainty metrics fail to flag ambiguous cases.
arXiv:2608.24518v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions, especially in scenarios with high-d...
FVeinSyn is a large‑scale synthetic finger‑vein image generator that separates vascular topology synthesis from imaging appearance rendering. It uses stochastic L‑systems to create anatomically valid, identity‑distinctive vein patterns, a cascaded region‑aware GAN to produce realistic near‑infrared images, and an intra‑class diversity generator to simulate realistic variations. The framework generated 500,000 images across 10,000 identities, and models trained with this data outperformed real‑data‑only baselines on eight public datasets, improving average accuracy by 27.43%.
arXiv:2608.21482v1 Announce Type: cross Abstract: Background: Multimodal fracture classifiers may benefit from patient and anatomical metadata, but they can also become brittle when contextual inform...
arXiv:2608. 14766v1 Announce Type: cross Abstract: Uncertainty estimation is critical for the safe clinical deployment of deep learning in medical image segmentation, with aleatoric uncertainty theoretically designed to capture irreducible data ambiguity.