Embedding-Driven Data Distillation for 360-Degree IQA With Residual-Aware Refinement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sendjasni, Abderrezzaq, Benkabou, Seif-Eddine, Larabi, Mohamed-Chaker
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914208551010304
author Sendjasni, Abderrezzaq
Benkabou, Seif-Eddine
Larabi, Mohamed-Chaker
author_facet Sendjasni, Abderrezzaq
Benkabou, Seif-Eddine
Larabi, Mohamed-Chaker
contents This article identifies and addresses a fundamental bottleneck in data-driven 360-degree image quality assessment (IQA): the lack of intelligent, sample-level data selection. Hence, we propose a novel framework that introduces a critical refinement step between patches sampling and model training. The core of our contribution is an embedding similarity-based selection algorithm that distills an initial, potentially redundant set of patches into a compact, maximally informative subset. This is formulated as a regularized optimization problem that preserves intrinsic perceptual relationships in a low-dimensional space, using residual analysis to explicitly filter out irrelevant or redundant samples. Extensive experiments on three benchmark datasets (CVIQ, OIQA, MVAQD) demonstrate that our selection enables a baseline model to match or exceed the performance of using all sampled data while keeping only 40-50% of patches. Particularly, we demonstrate the universal applicability of our approach by integrating it with several state-of-the-art IQA models, incleasy to deploy. Most significantly, its value as a generic,uding CNN- and transformer-based architectures, consistently enabling them to maintain or improve performance with 20-40\% reduced computational load. This work establishes that adaptive, post-sampling data refinement is a powerful and widely applicable strategy for achieving efficient and robust 360-degree IQA.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12667
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Embedding-Driven Data Distillation for 360-Degree IQA With Residual-Aware Refinement
Sendjasni, Abderrezzaq
Benkabou, Seif-Eddine
Larabi, Mohamed-Chaker
Computer Vision and Pattern Recognition
Machine Learning
This article identifies and addresses a fundamental bottleneck in data-driven 360-degree image quality assessment (IQA): the lack of intelligent, sample-level data selection. Hence, we propose a novel framework that introduces a critical refinement step between patches sampling and model training. The core of our contribution is an embedding similarity-based selection algorithm that distills an initial, potentially redundant set of patches into a compact, maximally informative subset. This is formulated as a regularized optimization problem that preserves intrinsic perceptual relationships in a low-dimensional space, using residual analysis to explicitly filter out irrelevant or redundant samples. Extensive experiments on three benchmark datasets (CVIQ, OIQA, MVAQD) demonstrate that our selection enables a baseline model to match or exceed the performance of using all sampled data while keeping only 40-50% of patches. Particularly, we demonstrate the universal applicability of our approach by integrating it with several state-of-the-art IQA models, incleasy to deploy. Most significantly, its value as a generic,uding CNN- and transformer-based architectures, consistently enabling them to maintain or improve performance with 20-40\% reduced computational load. This work establishes that adaptive, post-sampling data refinement is a powerful and widely applicable strategy for achieving efficient and robust 360-degree IQA.
title Embedding-Driven Data Distillation for 360-Degree IQA With Residual-Aware Refinement
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.12667