7 papers
Unifying Convolution and Attention via Convolutional Nearest Neighbors
Mingi Kang, Jeová Farias Sales Rocha Neto
Convolutional Neural Networks and Vision Transformers are the two dominant architectural families in computer vision, defined by spatially local convolution and global self-attenti…
IGLU: The Integrated Gaussian Linear Unit Activation Function
Mingi Kang, Zai Yang, Jeova Farias Sales Rocha Neto
Activation functions are fundamental to deep neural networks, governing gradient flow, optimization stability, and representational capacity. Within historic deep architectures, wh…
Interpolation between Convolution and Attention via K-Nearest Neighbors
Mingi Kang
The shift from Convolutional Neural Networks to Transformers has reshaped computer vision, yet these two architectural families are typically viewed as fundamentally distinct. Conv…
PanopMamba: Vision State Space Modeling for Nuclei Panoptic Segmentation
Ming Kang, Fung Fung Ting, Raphaël C. -W. Phan +2
Nuclei panoptic segmentation supports cancer diagnostics by integrating both semantic and instance segmentation of different cell types to analyze overall tissue structure and indi…
A Multimodal Feature Distillation with Mamba-Transformer Network for Brain Tumor Segmentation with Incomplete Modalities
Ming Kang, Fung Fung Ting, Shier Nee Saw +3
Existing brain tumor segmentation methods usually utilize multiple Magnetic Resonance Imaging (MRI) modalities in brain tumor images for segmentation, which can achieve better segm…
Parallel qMRI Reconstruction from 4x Accelerated Acquisitions
Mingi Kang
Magnetic Resonance Imaging (MRI) acquisitions require extensive scan times, limiting patient throughput and increasing susceptibility to motion artifacts. Accelerated parallel MRI…