4 papers
AdapterMoE: A Two-Stage Hard-Routing Mixture-of-Experts Architecture for Multi-Crop Disease Recognition with Calibrated Rejection and Incremental Learning
Pin-Hsun Huang, Shaou-Gang Miaou
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 fre…
Retrieval-Augmented Generation-Based Color Restoration for Low-Light Image Enhancement
Li-Wei Lu, Shaou-Gang Miaou
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 systemati…
EfficienT-HDR: An Efficient Transformer-Based Framework via Multi-Exposure Fusion for HDR Reconstruction
Yu-Shen Huang, Tzu-Han Chen, Cheng-Yen Hsiao +1
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 downstr…
Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement
Shyang-En Weng, Cheng-Yen Hsiao, Li-Wei Lu +4
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…