arXiv:2607. 13689v1 Announce Type: cross Abstract: We built a compact convolutional network (1.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
We built a compact convolutional network (1. 11 M parameters) for 46-class DHCD Devanagari recognition and reached 99.
arXiv:2607. 19393v1 Announce Type: cross Abstract: While auditing a perturbation-based OOD detector on a document benchmark, we recorded an AUROC of 0.
arXiv:2609.16859v1 Announce Type: cross Abstract: To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manua...
arXiv:2606. 01973v1 Announce Type: new Abstract: Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes.
To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manually. For a script that can be read by only a small...
The study investigates whether the number of discrete class‑separability jumps (phase transitions) observed during ResNet fine‑tuning can predict final test accuracy. Across 75 experiments on four benchmarks (CIFAR‑10, CIFAR‑100, TinyImageNet, CIFAR‑10‑C) and three ResNet variants, a strong negative correlation is found on standard i.i.d. datasets (r = −0.84 on CIFAR‑10, r = −0.87 on CIFAR‑100), while the correlation weakens under distributional stress. Additional analyses show that the transition count retains predictive power after controlling for architecture depth and outperforms other training‑curve signals on in‑distribution benchmarks, though it is dominated by other signals on stressed datasets.