← Back to all news
arXiv Computer Vision By Aon Safdar, Mohamed Saadeldin

Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging

Read the original on arXiv Computer Vision →

The paper introduces FAD‑ViT, a vision transformer that decouples spatial and feature axes of global attention, making feature‑axis attention the primary operator. Experiments on 23 medical imaging tasks show that shifting global attention from spatial to feature leaves from‑scratch performance unchanged but significantly boosts transfer learning, achieving up to three times the gain with fewer parameters and lower compute. The study demonstrates that prioritizing feature‑axis attention is a simple, cost‑effective design choice for improving medical image transfer.

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 Computer Vision.

Related stories

arXiv Computer Vision
Aug 25

Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images

arXiv:2605.05522v3 Announce Type: replace-cross Abstract: Although self-supervised pretraining is expected to learn broadly transferable representations, its effectiveness across imaging modalities s...

By Aneesh Rangnekar, Joao Miranda, Natally Horvat, Stephanie Chahwan, Samir Alrayess, Aditya Apte, Aditi Iyer, Eve LoCastro, Revathi Ravella, Marc J Gollub, Iva Petkovska, Jesse Joshua Smith, Paul Romesser, Julio Garcia-Aguilar, Harini Veeraraghavan, Joseph O Deasy
llmscomputer-visionfine-tuningbenchmarkssafety
More like this →
Hugging Face Trending Papers
Jul 12

Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification

Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classification losses rarely provide spatial supervision. Explicit supervision via anatomical shape information, such as segmentation masks of task-relevant anatomy, has been shown to guide the network toward regions relevant to the target prediction.

computer-visionsafety
More like this →
arXiv Computer Vision
Sep 7

DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models

DART is a new RGB‑D pretraining method for surgical vision foundation models that incorporates pseudo‑labeled depth maps as a pixel‑space reconstruction target during training. By adding a depth reconstruction head to DINOv2’s masked iBOT framework, DART improves representation quality without affecting downstream RGB‑only fine‑tuning or inference. Across eight surgical benchmarks—including segmentation, depth estimation, and image‑level recognition—DART outperforms both natural‑image and in‑domain baselines, demonstrating that geometric pseudo‑labels can strengthen foundation model pretraining without extra labels or inference cost.

By John J. Han, Adam Schmidt, Muhammad Abdullah Jamal, Jie Ying Wu, Omid Mohareri
computer-visionfine-tuningbenchmarks
More like this →