pyiqa.archs.maclip_arch

Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment

@article{liao2025beyond,

title={Beyond Cosine Similarity Magnitude-Aware CLIP for No-Reference Image Quality Assessment}, author={Liao, Zhicheng and Wu, Dongxu and Shi, Zhenshan and Mai, Sijie and Zhu, Hanwei and Zhu, Lingyu and Jiang, Yuncheng and Chen, Baoliang}, journal={arXiv preprint arXiv:2511.09948}, year={2025}

}

Accepted by AAAI 2026.

Reference:

• Arxiv link: https://arxiv.org/abs/2511.09948

• Official Github: https://github.com/zhix000/MA-CLIP

Module Contents

class pyiqa.archs.maclip_arch.CustomCLIP(backbone: str, device='cpu')

Bases: torch.nn.Module

forward(image, text, pos_embedding=False, text_features=None)

class pyiqa.archs.maclip_arch.MACLIP(model_type='clipiqa', backbone='RN50', pos_embedding=False)

Bases: torch.nn.Module

preprocess(img)

box_cox(x, lam=0.5, epsilon=1e-06)

fusion(cos, norm, base_cos=1.0, base_norm=0.6, alpha=1.0)

Parameters:

• box_lam – Lambda parameter for Box-Cox transformation (default: 0.5)

• base_cos/base_norm – Base weights for fusion of cosine similarity and magnitude cues (default: 1.0/0.6).

• alpha – Fusion coefficient (default: 1.0)

forward(x, box_lam=0.5, base_cos=1.0, base_norm=0.6, alpha=1.0)