Channel Attention for No-Reference Image Quality Assessment in DCT Domain

Attention mechanism, especially self-attention, has gained great success in image quality assessment. The advent of Transformer has led to a substantial enhancement in no-reference image quality assessment (NR-IQA). Existing works focus on leveraging the global perceptual capability of Transformer encoders to perceive image quality. In this work, we start from a different view and propose a novel multi-frequency channel attention framework for Transformer encoder. Through frequency analysis, we demonstrate mathematically that traditional global average pooling (GAP) is a specific instance of feature decomposition in the frequency domain. With the proof, we use the discrete cosine transform to compress channels, which optimally compresses channels by efficiently utilizing frequency components overlooked by GAP. The experimental results show that the proposed method leads to improvements of performance over the state-of-the-art methods.