5 papers
SSFMamba: Learning Symmetry-driven Spatial-Frequency Modeling for Physically Consistent 3D Medical Image Segmentation
Bo Zhang, Yifan Zhang, Shuo Yan +5
Accurate 3D medical image segmentation requires a delicate balance between fine-grained local details and global contextual understanding. While spatial-domain models often struggl…
A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion
Yu Bai, Zhe Wang, Jiarui Zhang +3
The trade-off between clean accuracy and adversarial robustness is a pervasive phenomenon in deep learning, yet its geometric origin remains elusive. In this work, we utilize Symme…
SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification
Yu Bai, Zitong Yu, Haowen Tian +11
We propose Spatial-Aware Correlated Multiple Instance Learning (SAC-MIL) for performing WSI classification. SAC-MIL consists of a positional encoding module to encode position info…
Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classification
Bo Zhang, Xu Xinan, Shuo Yan +4
Recent pseudo-bag augmentation methods for Multiple Instance Learning (MIL)-based Whole Slide Image (WSI) classification sample instances from a limited number of bags, resulting i…
BAISeg: Boundary Assisted Weakly Supervised Instance Segmentation
Tengbo Wang, Yu Bai
How to extract instance-level masks without instance-level supervision is the main challenge of weakly supervised instance segmentation (WSIS). Popular WSIS methods estimate a disp…