5 papers
Deep Unfolded Latent Optimally Partitioned-l2/l1 Networks for Data-driven Block-Sparse Recovery
Takanobu Furuhashi, Hidekata Hontani, Qibin Zhao +1
The convex Latent Optimal Partition (LOP)-l2/l1 approach enables block-sparse signal recovery with unknown partitions but relies on manual hyperparameter tuning. Additionally, nume…
Nonconvex Latent Optimally Partitioned Block-Sparse Recovery via Log-Sum and Minimax Concave Penalties
Takanobu Furuhashi, Hiroki Kuroda, Masahiro Yukawa +3
We propose two nonconvex regularization methods, LogLOP-l2/l1 and AdaLOP-l2/l1, for recovering block-sparse signals with unknown block partitions. These methods address the underes…
WEEP: A Differentiable Nonconvex Sparse Regularizer via Weakly-Convex Envelope
Takanobu Furuhashi, Hidekata Hontani, Qibin Zhao +1
Sparse regularization is fundamental in signal processing and feature extraction but often relies on non-differentiable penalties, conflicting with gradient-based optimizers. We pr…
Multi-Scale Representation of Follicular Lymphoma Pathology Images in a Single Hyperbolic Space
Kei Taguchi, Kazumasa Ohara, Tatsuya Yokota +4
We propose a method for representing malignant lymphoma pathology images, from high-resolution cell nuclei to low-resolution tissue images, within a single hyperbolic space using s…
Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion
Daiki Nishiyama, Hiroaki Miyoshi, Noriaki Hashimoto +4
Malignant lymphoma subtype classification directly impacts treatment strategies and patient outcomes, necessitating classification models that achieve both high accuracy and suffic…