Data-Efficient Image Quality Assessment with Attention-Panel Decoder

by   Guanyi Qin, et al.
Tsinghua University
Ocean University of China

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a novel BIQA pipeline based on the Transformer architecture, which achieves an efficient quality-aware feature representation with much fewer data. More specifically, we consider the traditional fine-tuning in BIQA as an interpretation of the pre-trained model. In this way, we further introduce a Transformer decoder to refine the perceptual information of the CLS token from different perspectives. This enables our model to establish the quality-aware feature manifold efficiently while attaining a strong generalization capability. Meanwhile, inspired by the subjective evaluation behaviors of human, we introduce a novel attention panel mechanism, which improves the model performance and reduces the prediction uncertainty simultaneously. The proposed BIQA method maintains a lightweight design with only one layer of the decoder, yet extensive experiments on eight standard BIQA datasets (both synthetic and authentic) demonstrate its superior performance to the state-of-the-art BIQA methods, i.e., achieving the SRCC values of 0.875 (vs. 0.859 in LIVEC) and 0.980 (vs. 0.969 in LIVE).


page 1

page 5


Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token

Image quality assessment is a fundamental problem in the field of image ...

Domain-Aware No-Reference Image Quality Assessment

No-reference image quality assessment (NR-IQA) is a fundamental yet chal...

MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion

Measuring the perceptual quality of images automatically is an essential...

Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network

We propose a deep bilinear model for blind image quality assessment (BIQ...

Collaborative Auto-encoding for Blind Image Quality Assessment

Blind image quality assessment (BIQA) is a challenging problem with impo...

Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment

Image Quality Assessment (IQA) constitutes a fundamental task within the...

Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment

The research in image quality assessment (IQA) has a long history, and s...

Please sign up or login with your details

Forgot password? Click here to reset