2 papers
cs.CV2025
Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstruction
Yujian Liu, Yuechuan Lin, Dongxu Shen +4
Whole-slide image (WSI) analysis remains challenging due to the gigapixel scale and sparsely distributed diagnostic regions. Multiple Instance Learning (MIL) mitigates this by mode…
cs.LG2024
The Implicit Bias of Gradient Descent on Separable Multiclass Data
Hrithik Ravi, Clayton Scott, Daniel Soudry +1
Implicit bias describes the phenomenon where optimization-based training algorithms, without explicit regularization, show a preference for simple estimators even when more complex…