6 papers
MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26
Sheng-Wei Chan, Chia-Min Lin, Hsin-Jui Pan +4
State space models (SSMs), notably Mamba, have recently emerged as efficient alternatives to self-attention with linear computational complexity. We investigate the integration of…
Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic Segmentation
Sheng-Wei Chan, Hsin-Jui Pan, Jen-Shiun Chiang
Mamba-based state space models offer linear-time long-range modeling for high-resolution dense prediction, but sequential state-space propagation can attenuate boundary-sensitive a…
ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion
Sheng-Wei Chan, Hsin-Jui Pan, Chun-Po Shen +3
Recent advances in semantic segmentation rely heavily on attention-based and transformer-style architectures that, while accurate, introduce considerable architectural complexity a…
DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization
Sheng-Wei Chan, Yung-Che Wang, Hsin-Jui Pan +2
Document image binarization aims to separate foreground text from degraded backgrounds while preserving thin, broken, and low-contrast strokes. Although deep learning methods have…
ERN-Net : Evolving Reason Node-Net for Document Binarization
Hsin-Jui Pan, Sheng-Wei Chan, Jen-Shiung Chiang
This paper presents ERN-Net, an Evolving Reason Node-Net for efficient document image binarization. ERN-Net enhances degradation-sensitive regions, such as faint strokes, broken ch…
Generalizing Geometry-Guided Mamba as a Plug-and-Play Context Module for CNN-based Semantic Segmentation
Sheng-Wei Chan, Hsin-Jui Pan, Chun-Po Shen +3
CNN-based semantic segmentation networks usually rely on context heads such as ASPP, PPM, or attention modules to enlarge the receptive field. These heads are effective but may int…