arXiv:2505. 04397v2 Announce Type: replace-cross Abstract: Modern vision networks are dominated by additive local transformations, whereas explicit multiplicative local interactions remain underexplored.
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.
arXiv:2606. 20035v1 Announce Type: cross Abstract: Many dense prediction networks rely on additive feature transformations and model higher-order feature interactions only implicitly.
arXiv:2604.19609v2 Announce Type: replace Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...
arXiv:2608.22619v1 Announce Type: cross Abstract: Generative segmentation provides an alternative to direct pixel-wise prediction by operating on learned latent representations, but effective image-t...
arXiv:2603.02843v2 Announce Type: replace Abstract: Generalisation across image scales remains a fundamental challenge for deep networks, which often fail to handle images at scales not seen during t...
MTMed3D is a multi-task Transformer-based model that jointly performs 3D detection, segmentation, and classification in medical imaging. It uses a shared Transformer encoder to produce multi-scale features, with separate CNN decoders for each task. Evaluated on BraTS 2018 and 2019, it achieves strong results, especially in detection, while reducing computational cost and inference time compared to single-task models.
The study evaluates four deep‑learning segmentation architectures—Unet, PSPNet, Linknet, and FPN—paired with six pre‑trained encoders to predict COVID‑19 lesions in CT images. Experiments on three COVID‑19 CT datasets show high accuracy, achieving a maximum binary F1‑score of 98% and multi‑class F1‑scores of 75% and 77%. The work aims to provide a standardized performance benchmark for medical image segmentation and a reference for other imaging scenarios.