Published In
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Document Type
Pre-Print
Publication Date
2025
Subjects
Neural Networks -- Computer Science
Abstract
For full-reference image quality assessment (FR-IQA) using deep-learning approaches, the perceptual similarity score between a distorted image and a reference image is typically computed as a distance measure between features extracted from a pretrained CNN or more recently, a Transformer network. Often, these intermediate features require further fine-tuning or processing with additional neural network layers to align the final similarity scores with human judgments. So far, most IQA models based on foundation models have primarily relied on the final layer or the embedding for the quality score estimation. In contrast, this work explores the potential of utilizing the intermediate features of these foundation models, which have largely been unexplored so far in the design of low-level perceptual similarity metrics. We demonstrate that the intermediate features are comparatively more effective. Moreover, without requiring any training, these metrics can outperform both traditional and state-of-the-art learned metrics by utilizing distance measures between the features. Code: https://github.com/abhijay9/ZS-IQA
Rights
Copyright (c) 2025 The Authors
Locate the Document
DOI
10.1109/ICASSP49660.2025.10889302
Persistent Identifier
https://archives.pdx.edu/ds/psu/43130
Publisher
IEEE
Citation Details
Published as: Ghildyal, A., Barman, N., & Zadtootaghaj, S. (2025). Foundation Models Boost Low-Level Perceptual Similarity Metrics. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1–5. https://doi.org/10.1109/icassp49660.2025.10889302
Description
This is the author’s version of a work that was accepted for publication. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published as: Foundation Models Boost Low-Level Perceptual Similarity Metrics. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1–5.