Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling

TL;DR

Life-IQA introduces a novel GCN-enhanced layer interaction and MoE-based feature decoupling framework to improve blind image quality assessment, achieving state-of-the-art results by effectively leveraging shallow and deep features.

Contribution

The paper proposes a new BIQA framework with GCN-enhanced layer interaction and MoE-based feature decoupling, addressing the unequal contribution of features and exploring quality decoding architectures.

Findings

Outperforms existing BIQA methods on multiple benchmarks.

Balances accuracy and computational cost effectively.

Demonstrates the effectiveness of GCN and MoE modules in BIQA.

Abstract

Blind image quality assessment (BIQA) plays a crucial role in evaluating and optimizing visual experience. Most existing BIQA approaches fuse shallow and deep features extracted from backbone networks, while overlooking the unequal contributions to quality prediction. Moreover, while various vision encoder backbones are widely adopted in BIQA, the effective quality decoding architectures remain underexplored. To address these limitations, this paper investigates the contributions of shallow and deep features to BIQA, and proposes a effective quality feature decoding framework via GCN-enhanced \underline{l}ayer\underline{i}nteraction and MoE-based \underline{f}eature d\underline{e}coupling, termed \textbf{(Life-IQA)}. Specifically, the GCN-enhanced layer interaction module utilizes the GCN-enhanced deepest-layer features as query and the penultimate-layer features as key, value, then performs cross-attention to achieve feature interaction. Moreover, a MoE-based feature decoupling module is proposed to decouple fused representations though different experts specialized for specific distortion types or quality dimensions. Extensive experiments demonstrate that Life-IQA shows more favorable balance between accuracy and cost than a vanilla Transformer decoder and achieves state-of-the-art performance on multiple BIQA benchmarks.The code is available at: \href{https://github.com/TANGLONG2/Life-IQA/tree/main}{\texttt{Life-IQA}}.