arXiv subjects

Shaou-Gang Miaou

Publications and source records attributed to Shaou-Gang Miaou.

5 recordsLinked to original sources

arXiv2026

AdapterMoE: A Two-Stage Hard-Routing Mixture-of-Experts Architecture for Multi-Crop Disease Recognition with Calibrated Rejection and Incremental Learning

Timely crop-disease identification is critical to food security. Multi-crop recognition suits Mixture-of-Experts (MoE), but conventional soft-routing MoE learns crop assignment freely end-to-end, letting a few experts dominate (expert collapse) with no semantic correspondence to crops, and facing high retraining costs, unstable rejection of non-target inputs, and a saturated accuracy ceiling. We shift the objective from accuracy toward a trade-off among deployment cost, scaling flexibility, and rejection stability, using deterministic hard routing. We propose AdapterMoE: a RouterHead classifies the crop and rejects non-target crops via a Maximum Softmax Probability threshold, with a dual-gate Energy+KNN out-of-distribution module catching distribution-shifted inputs; five per-crop Adapters atop a frozen EfficientNet-B0 backbone discriminate diseases, each calibrated via Temperature Scaling. Because experts are hard-isolated at the data level, the design avoids expert collapse and exposes an add_crop interface for local, per-crop updates instead of full retraining. On PlantVillage (5 crops, 26 classes), across a fair five-system comparison, AdapterMoE attains accuracy statistically indistinguishable from the best baselines (Macro-F1 within a 0.24-point band) while cutting training cost to about 9% of full-network baselines, expanding to a new crop in

cs.CV↗

arXiv2026

Retrieval-Augmented Generation-Based Color Restoration for Low-Light Image Enhancement

Recent low-light image enhancement (LLIE) methods have driven brightness and structural fidelity close to that of normally-exposed images, yet their outputs still exhibit systematic color shifts such as greenish skies, yellowish faces, and warm-tinted white objects. We attribute this to end-to-end LLIE training coupling brightness, structure, and color within a single network, leaving the color channels weakly supervised. We recast color restoration as an independent sub-problem and decouple it from brightness enhancement, realizing it as a general-purpose post-processing module built on retrieval-augmented generation (RAG). Rather than relying solely on parametric color priors learned during training, the module dynamically retrieves a reference image from an external high-quality color knowledge base and injects its color distribution into a color-restoration network to correct residual bias. The design has three components: (i) a dual-index FAISS retriever built on intermediate VGG19 features, capturing textural and structural similarity through global mean and variance statistics; (ii) GlobalSPHistAdaIN, which reduces the reference spatial-preserving color histogram to a global color vector and modulates network features via adaptive instance normalization, removing dependence on pixel-level correspondence; and (iii) a residual formulation that predicts a color correction over the front-end output. Across LOLv1, LOLv2-Real, and LOLv2-Synthetic, the module consistently improves color-specific metrics, and it remains effective when the front end is swapped among CPGA-Net++, LLFormer, FLIGHTNet, and IAT, confirming cross-front-end generality. Ablations show that a VGG19 dual index outperforms CLIP-based retrieval, indicating that color restoration depends on textural and structural similarity rather than high-level semantics.

eess.IV↗

arXiv2025

EfficienT-HDR: An Efficient Transformer-Based Framework via Multi-Exposure Fusion for HDR Reconstruction

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous driving. Multi-Exposure Fusion (MEF) is a mainstream technique to achieve this goal; however, existing methods generally face the dual bottlenecks of high computational costs and ghosting artifacts, hindering their widespread deployment. To this end, this study proposes a light-weight Vision Transformer architecture designed explicitly for HDR reconstruction to overcome these limitations. This study is based on the Context-Aware Vision Transformer and begins by converting input images to the YCbCr color space to separate luminance and chrominance information. It then employs an Intersection-Aware Adaptive Fusion (IAAF) module to suppress ghosting effectively. To further achieve a light-weight design, we introduce Inverted Residual Embedding (IRE), Dynamic Tanh (DyT), and propose Enhanced Multi-Scale Dilated Convolution (E-MSDC) to reduce computational complexity at multiple levels. Our study ultimately contributes two model versions: a main version for high visual quality and a light-weight version with advantages in computational efficiency, both of which achieve an excellent balance between performance and image quality. Experimental results demonstrate that, compared to the baseline, the main version reduces FLOPS by approximately 67% and increases inference speed by more than fivefold on CPU and 2.5 times on an edge device. These results confirm that our method provides an efficient and ghost-free HDR imaging solution for edge devices, demonstrating versatility and practicality across various dynamic scenarios.

cs.CV↗

arXiv2025

Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement

Enhancing low-light images remains a critical challenge in computer vision, as does designing lightweight models for edge devices that can handle the computational demands of deep learning. This article introduces an extended version of the Channel-Prior and Gamma-Estimation Network (CPGA-Net), termed CPGA-Net+, incorporating the theoretically-based Attentions for illumination in local and global processing. Additionally, we assess our approach through a theoretical analysis of the block design by introducing both an ultra-lightweight and a stronger version, following the same design principles. The lightweight version significantly reduces computational costs by over two-thirds by utilizing the local branch as an auxiliary component. Meanwhile, the stronger version achieves an impressive balance by maximizing local and global processing capabilities. Our proposed methods have been validated as effective compared to recent lightweight approaches, offering superior performance and scalable solutions with limited computational resources.

eess.IV↗

arXiv2024

A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction

Human vision relies heavily on available ambient light to perceive objects. Low-light scenes pose two distinct challenges: information loss due to insufficient illumination and undesirable brightness shifts. Low-light image enhancement (LLIE) refers to image enhancement technology tailored to handle this scenario. We introduce CPGA-Net, an innovative LLIE network that combines dark/bright channel priors and gamma correction via deep learning and integrates features inspired by the Atmospheric Scattering Model and the Retinex Theory. This approach combines the use of traditional and deep learning methodologies, designed within a simple yet efficient architectural framework that focuses on essential feature extraction. The resulting CPGA-Net is a lightweight network with only 0.025 million parameters and 0.030 seconds for inference time, yet it achieves superior performance over existing LLIE methods on both objective and subjective evaluation criteria. Furthermore, we utilized knowledge distillation with explainable factors and proposed an efficient version that achieves 0.018 million parameters and 0.006 seconds for inference time. The proposed approaches inject new solution ideas into LLIE, providing practical applications in challenging low-light scenarios.

eess.IV↗