Xiaosong Li

Huichun Liu, Xiaosong Li, Tianshu Tan

Image dehazing aims to restore clean images from hazy ones. Convolutional Neural Networks (CNNs) and Transformers have demonstrated exceptional performance in local and global feature extraction, respectively, and currently represent the two mainstream frameworks in image dehazing. In this paper, we propose a novel dual-branch image dehazing framework that guides CNN and Transformer components interactively. We reconsider the complementary characteristics of CNNs and Transformers by leveraging the differential relationships between global and local features for interactive guidance. This approach enables the capture of local feature positions through global attention maps, allowing the CNN to focus solely on feature information at effective positions. The single-branch Transformer design ensures the network's global information recovery capability. Extensive experiments demonstrate that our proposed method yields competitive qualitative and quantitative evaluation performance on both synthetic and real public datasets. Codes are available at https://github.com/Feecuin/Two-Branch-Dehazing

Zhongqian Fu, Ning Ding, Kai Han et al.

Mixture-of-Experts (MoE) models have emerged as a cornerstone of large-scale deep learning by efficiently distributing computation and enhancing performance. However, their unique architecture-characterized by sparse expert activation and dynamic routing mechanisms-introduces inherent complexities that challenge conventional quantization techniques. Existing post-training quantization (PTQ) methods struggle to address activation outliers, router consistency and sparse expert calibration, leading to significant performance degradation. To bridge this gap, we propose EAQuant, a novel PTQ framework tailored for MoE architectures. Our method systematically tackles these challenges through three key innovations: (1) expert-aware smoothing aggregation to suppress activation outliers and stabilize quantization, (2) router logits distribution alignment to preserve expert selection consistency post-quantization, and (3) expert-level calibration data balance to optimize sparsely activated experts. Extensive experiments across W4A4 and extreme W3A4 quantization configurations demonstrate that EAQuant significantly outperforms existing methods, achieving average score improvements of 1.15 - 2.28% across three diverse MoE architectures, with particularly pronounced gains in reasoning tasks and robust performance retention under aggressive quantization. By integrating these innovations, EAQuant establishes a new state-of-the-art for high-precision, efficient MoE model compression. Our code is available at https://github.com/darren-fzq1/EAQuant.