Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

03/27/2023
by   Weixia Zhang, et al.
0

We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary knowledge from other tasks, in a way that the model parameter sharing and the loss weighting are determined automatically. Specifically, we first describe all candidate label combinations (from multiple tasks) using a textual template, and compute the joint probability from the cosine similarities of the visual-textual embeddings. Predictions of each task can be inferred from the joint distribution, and optimized by carefully designed loss functions. Through comprehensive experiments on learning three tasks - BIQA, scene classification, and distortion type identification, we verify that the proposed BIQA method 1) benefits from the scene classification and distortion type identification tasks and outperforms the state-of-the-art on multiple IQA datasets, 2) is more robust in the group maximum differentiation competition, and 3) realigns the quality annotations from different IQA datasets more effectively. The source code is available at https://github.com/zwx8981/LIQE.

READ FULL TEXT

page 1

page 7

research
06/17/2021

A Multi-task convolutional neural network for blind stereoscopic image quality assessment using naturalness analysis

This paper addresses the problem of blind stereoscopic image quality ass...
research
11/02/2019

Domain-Aware No-Reference Image Quality Assessment

No-reference image quality assessment (NR-IQA) is a fundamental yet chal...
research
05/24/2023

Collaborative Auto-encoding for Blind Image Quality Assessment

Blind image quality assessment (BIQA) is a challenging problem with impo...
research
09/15/2022

Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment

Recent years have witnessed the great success of blind image quality ass...
research
12/12/2016

An Attention-Driven Approach of No-Reference Image Quality Assessment

In this paper, we present a novel method of no-reference image quality a...
research
05/14/2021

Troubleshooting Blind Image Quality Models in the Wild

Recently, the group maximum differentiation competition (gMAD) has been ...
research
08/10/2020

Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment

Currently, most image quality assessment (IQA) models are supervised by ...

Please sign up or login with your details

Forgot password? Click here to reset