arXiv subjects

Chia-Min Lin

Publications and source records attributed to Chia-Min Lin.

At least 19 recordsLinked to original sources

arXiv2026

SFMformer: A Spatial-Frequency Modulation Transformer for Lightweight Image Super-Resolution

Sparse attention mechanisms, which score all token pairs but propagate only the strongest, now underpin the most efficient Transformers for lightweight image super-resolution. This paper observes that sparsification changes what it means to improve such a network. A dense attention layer has one place where representation quality matters: the aggregation of attended features. A sparse layer has two, because the top-k operator first decides which tokens survive and only then decides what to do with them, and a token discarded at the selection stage cannot be recovered downstream. Selection quality and aggregation quality are therefore separable targets, addressed by modules placed before and after the attention respectively. We test this by pairing a dual-branch spatial enhancement on the input of a progressive focused attention with a wavelet-domain modulation on its output, forming SFMformer. Measuring each module alone and jointly over all fifteen benchmark-scale pairs, we find their gains are not additive: the joint gain exceeds the sum of the individual gains on nine pairs, and the sign of the discrepancy is predicted by how much the weaker module contributes on its own (r = -0.72), so the two compound when they relieve different constraints and overlap when they relieve the same one. Enabling spectral modulation once per block rather than once per layer retains the effect at roughly one-sixth of its cost, keeping the model below one million parameters at every scale. SFMformer ranks first on 28 of 30 PSNR/SSIM entries across five benchmarks and three upscaling factors. We report the cases where the pairing does not help, and deploy the model on a Raspberry Pi 5 to confirm the design is practical under tight resource budgets.

cs.CV↗

arXiv2026

MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26

State space models (SSMs), notably Mamba, have recently emerged as efficient alternatives to self-attention with linear computational complexity. We investigate the integration of Mamba into YOLO26, the latest non-maximum suppression (NMS)-free object detection framework, by proposing MambaPSA, a lightweight Mamba-based replacement for the C2PSA block at the end of the backbone. To complement this study, we additionally insert a bidirectional Vision Mamba (BiViM) module at the P3, P4, and P5 levels of the neck. Experiments on PASCAL VOC 2007+2012 show that MambaPSA reduces parameters by 2.9%, FLOPs by 12.1%, and improves CPU inference throughput by 17.6% (from 17 to 20 FPS) with negligible accuracy change (-0.1 mAP50:95), while the P4 BiViM placement yields the best accuracy gain (+0.9 mAP50:95). These results suggest that SSMs offer a favorable efficiency-accuracy trade-off when replacing attention-based blocks in NMS-free lightweight detectors.

cs.CV↗

arXiv2026

YOLO-AMC: An Improved YOLO Architecture with Attention Mechanisms for Building Crack Detection

Crack detection plays an important role in infrastructure inspection and Structural Health Monitoring (SHM). However, cracks typically appear as thin, low-contrast structures and are easily affected by background noise, posing challenges for existing object detection models. This study proposes an improved YOLO-based architecture with integrated attention mechanisms, termed YOLO-AMC (YOLO with Attention Mechanisms for Crack Detection), to enhance automated crack detection performance. Based on YOLOv11, the original C2PSA module is removed, and multiple attention mechanisms, including Global Attention Mechanism (GAM), Residual Convolutional Block Attention Module (Res-CBAM), and Shuffle Attention (SA), are introduced into the multi-scale feature fusion layers of the Neck to strengthen cross-scale feature integration. Experimental results demonstrate that YOLO-AMC consistently outperforms baseline models YOLOv11n and YOLOv8n across multiple evaluation metrics. Among the evaluated attention modules, GAM achieves the best detection performance, obtaining mAP@0.5 = 0.9917 and mAP@0.5:0.95 = 0.9506 on the test dataset, which are higher than those of YOLOv11 (0.9833 / 0.9112) and YOLOv8 (0.9707 / 0.8921). Furthermore, while maintaining a computational complexity of 7.6 GFLOPs, the proposed model achieves 110.95 FPS on an NVIDIA RTX 4090 platform and approximately 5 FPS on a Raspberry Pi 5 edge device, demonstrating a favorable trade-off between accuracy and deployment efficiency. The implementation code for this study is available on GitHub at https://github.com/CY-Tsai24/YOLO-AMC.

cs.CV↗

arXiv2026

Natural Inflation with a negative cosmological constant

In this work, we investigate a cosmic inflation model based on a cosine-type potential with a negative cosmological constant. This model originates from a classical solution of the Wheeler-DeWitt equation. The equation of motion for the inflaton field can be solved analytically without relying on approximation schemes, such as the slow-roll conditions. The predictions of the spectral index, the tensor-to-scalar ratio, and the running spectral index are calculated and compared with experimental constraints from Planck Collaboration, Atacama Cosmology Telescope Collaboration (ACT), and Dark Energy Spectroscopic Instrument (DESI).

gr-qc↗

arXiv2026

DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization

Document image binarization aims to separate foreground text from degraded backgrounds while preserving thin, broken, and low-contrast strokes. Although deep learning methods have improved binarization performance, most existing approaches rely on convolutional, transformer-based, or generative architectures, while Mamba-based state space models remain largely unexplored for this task. In this work, we investigate Mamba-based feature propagation and observe that direct state-space propagation may dilute weak foreground cues during long-range modeling, especially faint ink traces, fragmented characters, and boundary-sensitive stroke details. To address this problem, we propose DeepMine-Mamba, a Mamba-based binarization framework equipped with a novel Anti-Dilution Gate that estimates propagation-induced feature changes and selectively restores stroke-sensitive local responses while suppressing unnecessary background enhancement. Experiments on DIBCO/H-DIBCO benchmarks under a strict leave-one-year-out protocol show that DeepMine-Mamba achieves competitive overall performance, with strong average FM and Fps across benchmark years. Ablation results further show that the Anti-Dilution Gate is the key component for mitigating propagation-induced foreground dilution and improving stroke preservation.

cs.CV↗

arXiv2026

Generalizing Geometry-Guided Mamba as a Plug-and-Play Context Module for CNN-based Semantic Segmentation

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 introduce heavy computation, memory cost, or boundary leakage. This paper revisits Directional Geometric Mamba (G-Mamba) from DGM-Net and studies it as a plug-and-play context aggregation module rather than a complete new segmentation architecture. The key idea is to inject geometric guidance into the selective scan process, allowing long-range feature propagation to be modulated by boundary and centripetal-flow cues. We replace the original context heads of six representative CNN segmentation models, including DeepLabV3+, DANet, CCNet, PSPNet, PSANet, and OCRNet, while keeping the ResNet-101 backbone unchanged. Results on Cityscapes show consistent mIoU gains with only moderate extra GFLOPs at $1024\times1024$ resolution, suggesting that geometry-guided SSM modules can serve as practical alternatives or enhancements to conventional CNN context heads.

cs.CV↗

arXiv2026

ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion

Recent advances in semantic segmentation rely heavily on attention-based and transformer-style architectures that, while accurate, introduce considerable architectural complexity and computational cost. This paper asks whether a compact CNN-based segmentation head can remain competitive by adaptively selecting useful receptive-field evidence. We propose ATV-Net, an Adaptive Triple-View Network that attaches a lightweight head to a conventional backbone. The head organizes three complementary views -- point-wise, neighborhood-level, and enlarged context -- and fuses them through an Adaptive Decision Gate that generates image-dependent weights from global feature statistics. This allows the model to emphasize different receptive-field responses according to scene content, without dense attention or multi-scale aggregation. Experiments on Cityscapes and Pascal VOC 2012 show that ATV-Net achieves 80.31% mIoU on Cityscapes with ResNet-101 and 80.90% with ConvNeXt-Tiny, and 86.7% and 88.5% mIoU on Pascal VOC 2012, respectively, while requiring fewer GFLOPs than representative context-aggregation and attention-based heads. The results indicate that adaptive receptive-field selection remains a practical and effective design choice for CNN-based semantic segmentation.

cs.CV↗

arXiv2026

FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation

We present FoR-Net, an efficient semantic segmentation framework that focuses on identifying and enhancing hard regions. Instead of relying on heavy global modeling, FoR-Net adopts an efficient strategy that selectively emphasizes informative regions through a learned importance map and a Top-K activation mechanism. Specifically, a selector module predicts region-wise importance, enabling the model to focus on challenging areas such as thin structures and object boundaries. Multi-scale reasoning is achieved using convolutional branches with different receptive fields, allowing diverse spatial context aggregation. We evaluate FoR-Net on the Cityscapes benchmark under limited computational resources. Despite its efficient design and standard training configuration, FoR-Net achieves competitive performance and exhibits improved attention to difficult regions. These results suggest that selective region-focused reasoning can serve as a practical and efficient alternative for semantic segmentation. This work explores region-focused reasoning under resource-constrained settings and provides insights for developing efficient and region-aware segmentation models.

cs.CV↗

arXiv2026

Simple Analytical Solutions of the Wheeler-DeWitt Equation in the Classical Hamilton-Jacobi Limit

We investigate the Wheeler-DeWitt equation for a flat, homogeneous, and isotropic Universe containing a canonical scalar field with a potential. We show that under the constraint $|\Psi|=1$, where the Wheeler-DeWitt equation exactly becomes the classical Hamilton-Jacobi equation, the form of the potential is completely determined depending on the value of the operator ordering parameter. Furthermore, we demonstrate that the classified potentials admit simple forms, such as the exponential, quadratic with a negative cosmological constant, and cosine-type potential with a negative cosmological constant. Several of these have already been explored in the context of inflation or dark energy. Finally, focusing on the system with the cosine-type potential and a negative cosmological constant in the classified potentials, we derive the analytical solutions for the scale factor and the scalar field and discuss the cosmological implications.

hep-th↗

arXiv2026

Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation

High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher computational budgets. While effective, such approaches introduce substantial computational overhead and limit accessibility under constrained hardware settings. In this paper, we propose DGM-Net (Directional Geometric Mamba Network), an efficient architecture that improves modeling capability through structural design rather than increasing model capacity. We introduce Directional Geometric Mamba (G-Mamba), a linear-complexity O(N) operator as an alternative to conventional context modeling modules such as ASPP and PPM. To further enhance structural awareness in state space model (SSM)-based modeling, we design the DGM-Module, which extracts centripetal flow fields and topological skeletons to guide the scanning process and improve boundary preservation. Without relying on large-scale pretraining or heavy backbone scaling, DGM-Net achieves 80.8% mIoU within 28k iterations, 82.3% mIoU on Cityscapes test set, and 45.24% mIoU on ADE20K. In addition, the model maintains stable performance under constrained hardware settings (e.g., batch size of 2 on 8GB VRAM), highlighting its efficiency and practicality. These results demonstrate that incorporating geometric guidance into SSM-based architectures provides an effective and resource-efficient direction for semantic segmentation.

cs.CV↗

arXiv2024

Machine Learning and First-Principles Predictions of Materials with Low Lattice Thermal Conductivity

We perform machine learning (ML) simulations and density functional theory (DFT) calculations to search for materials with low lattice thermal conductivity, $\kappa_L$. Several cadmium (Cd) compounds containing elements from the alkali-metal and carbon groups including A$_2$CdX (A = Li, Na, and K; X = Pb, Sn, and Ge) are predicted by our ML models to exhibit very low $\kappa_L$ values ($< 1.0 $ W/mK), rendering these materials suitable for potential thermal management and insulation applications. Further DFT calculations of electronic and transport properties indicate that the figure of merit, $ZT$, for thermoelectric performance can exceed 1.0 in compounds such as K$_2$CdPb, K$_2$CdSn, and K$_2$CdGe, which are thereby also promising thermoelectric materials.

cond-mat.mtrl-sci↗

arXiv2024

Primordial perturbations in Type III hilltop inflation models

We analytically compute the power spectrum of primordial curvature perturbations in Type III hilltop inflation models under the slow-roll approximation. The model parameters are constrained using current Cosmic Microwave Background (CMB) data. The curvature perturbations that exit the horizon at small scales show sufficiently large amplitudes to produce primordial black holes (PBHs). We then consider the quantum one-loop corrections in these models from both the self-interaction of the inflaton and its interaction with the waterfall field. We show the loop corrections in both cases for 60 e-folds of inflation are negligible, ensuring the tree-level results are reliable within the chosen parameter regime.

gr-qc↗

arXiv2024

Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detection

Children often suffer wrist injuries in daily life, while fracture injuring radiologists usually need to analyze and interpret X-ray images before surgical treatment by surgeons. The development of deep learning has enabled neural network models to work as computer-assisted diagnosis (CAD) tools to help doctors and experts in diagnosis. Since the YOLOv8 models have obtained the satisfactory success in object detection tasks, it has been applied to fracture detection. The Global Context (GC) block effectively models the global context in a lightweight way, and incorporating it into YOLOv8 can greatly improve the model performance. This paper proposes the YOLOv8+GC model for fracture detection, which is an improved version of the YOLOv8 model with the GC block. Experimental results demonstrate that compared to the original YOLOv8 model, the proposed YOLOv8-GC model increases the mean average precision calculated at intersection over union threshold of 0.5 (mAP 50) from 63.58% to 66.32% on the GRAZPEDWRI-DX dataset, achieving the state-of-the-art (SOTA) level. The implementation code for this work is available on GitHub at https://github.com/RuiyangJu/YOLOv8_Global_Context_Fracture_Detection.

cs.CV↗

arXiv2023

Uniform rate inflation on the brane

We propose a model of uniform rate inflation on the brane. The potential is given by a hyperbolic cosine function plus a negative cosmological constant. The equation of motion is solved analytically without using slow-roll approximation. The result is that the inflaton field is rolling at a constant speed. The prediction for cosmological perturbations depends on the field value at the end of inflation. The experimental constraints could be satisfied in the parameter space.

hep-ph↗

arXiv2023

Quantum Loop effects to Primordial perturbations at the end of Type III hilltop inflation models

In this work, we analytically calculate the spectra of primordial perturbations at the end of Type III hilltop inflation models under the slow-roll approximation. We examine the one-loop corrections of the spectra and find that those from the inflaton self-interaction are negligible. On the contrary, the loop effects from the interaction between the inflaton field and the waterfall field can be significant when the vacuum expectation value of the waterfall field is small. The implications are discussed.

astro-ph.CO↗

arXiv2023

The average equation of state for the oscillating inflaton field of the simplest $\alpha$-attractor E-model

In this work, we calculate the average equation of state for the oscillating inflaton field of the simplest $\alpha$-attractor E-model. We show that the average equation of state can be solved analytically. We discover that when $\alpha$ is small, the average equation of state of the oscillating inflaton field approaches that of a cosmological constant. This is the phenomenon of oscillating inflation.

hep-ph↗

arXiv2023

On the oscillations of the inflaton field of the simplest $\alpha$-attractor T-model

In this work, we consider homogeneous oscillations of the inflaton field after inflation. In particular, we obtain an analytical result for the (average) equation of state for the oscillating inflaton field for the simplest $\alpha$-attractor T-model. We also study the post-inflationary evolution before inflaton decay. It is possible that during inflaton field oscillation, the (average) equation of state is that of a cosmological constant. This leads to the phenomenon of oscillating inflation. However, we show that the duration of oscillating inflation is very limited.

hep-ph↗