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

arXiv: https://arxiv.org/abs/2412.12667 · HTML: https://mlsanity.com/paper/2412.12667/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 38 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks](https://mlsanity.com/paper/2002.09140/) (2020)
- [ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Images](https://mlsanity.com/paper/2103.13922/) (2021)
- [Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment](https://mlsanity.com/paper/2305.10983/) (2023)
- [Spatial Attention-based Non-reference Perceptual Quality Prediction Network for Omnidirectional Images](https://mlsanity.com/paper/2103.06116/) (2021)
- [ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers](https://mlsanity.com/paper/2303.06907/) (2023)
- [Instance Selection Improves Geometric Mean Accuracy: A Study on Imbalanced Data Classification](https://mlsanity.com/paper/1804.07155/) (2018)

## Abstract (arXiv)

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.