MSLIQA:通过多尺度学习增强图像质量评估的学习表示法

Nasim Jamshidi Avanaki, Abhijay Ghildiyal, Nabajeet Barman, Saman Zadtootaghaj
{"title":"MSLIQA:通过多尺度学习增强图像质量评估的学习表示法","authors":"Nasim Jamshidi Avanaki, Abhijay Ghildiyal, Nabajeet Barman, Saman Zadtootaghaj","doi":"arxiv-2408.16879","DOIUrl":null,"url":null,"abstract":"No-Reference Image Quality Assessment (NR-IQA) remains a challenging task due\nto the diversity of distortions and the lack of large annotated datasets. Many\nstudies have attempted to tackle these challenges by developing more accurate\nNR-IQA models, often employing complex and computationally expensive networks,\nor by bridging the domain gap between various distortions to enhance\nperformance on test datasets. In our work, we improve the performance of a\ngeneric lightweight NR-IQA model by introducing a novel augmentation strategy\nthat boosts its performance by almost 28\\%. This augmentation strategy enables\nthe network to better discriminate between different distortions in various\nparts of the image by zooming in and out. Additionally, the inclusion of\ntest-time augmentation further enhances performance, making our lightweight\nnetwork's results comparable to the current state-of-the-art models, simply\nthrough the use of augmentations.","PeriodicalId":501480,"journal":{"name":"arXiv - CS - Multimedia","volume":"9 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MSLIQA: Enhancing Learning Representations for Image Quality Assessment through Multi-Scale Learning\",\"authors\":\"Nasim Jamshidi Avanaki, Abhijay Ghildiyal, Nabajeet Barman, Saman Zadtootaghaj\",\"doi\":\"arxiv-2408.16879\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"No-Reference Image Quality Assessment (NR-IQA) remains a challenging task due\\nto the diversity of distortions and the lack of large annotated datasets. Many\\nstudies have attempted to tackle these challenges by developing more accurate\\nNR-IQA models, often employing complex and computationally expensive networks,\\nor by bridging the domain gap between various distortions to enhance\\nperformance on test datasets. In our work, we improve the performance of a\\ngeneric lightweight NR-IQA model by introducing a novel augmentation strategy\\nthat boosts its performance by almost 28\\\\%. This augmentation strategy enables\\nthe network to better discriminate between different distortions in various\\nparts of the image by zooming in and out. Additionally, the inclusion of\\ntest-time augmentation further enhances performance, making our lightweight\\nnetwork's results comparable to the current state-of-the-art models, simply\\nthrough the use of augmentations.\",\"PeriodicalId\":501480,\"journal\":{\"name\":\"arXiv - CS - Multimedia\",\"volume\":\"9 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.16879\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.16879","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

无参考图像质量评估(NR-IQA)仍然是一项极具挑战性的任务,原因在于失真现象的多样性和缺乏大型注释数据集。许多研究都试图通过开发更精确的无参考图像质量评估模型(通常采用复杂且计算成本高昂的网络),或者通过弥合各种失真之间的领域差距来提高测试数据集上的性能,从而应对这些挑战。在我们的工作中,我们通过引入一种新颖的增强策略,提高了通用轻量级 NR-IQA 模型的性能,使其性能提升了近 28%。这种增强策略使网络能够通过放大和缩小图像,更好地分辨图像不同部分的不同失真。此外,测试时间增强功能的加入进一步提高了性能,使得我们的轻量级网络仅通过使用增强功能就能与当前最先进的模型相媲美。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
MSLIQA: Enhancing Learning Representations for Image Quality Assessment through Multi-Scale Learning
No-Reference Image Quality Assessment (NR-IQA) remains a challenging task due to the diversity of distortions and the lack of large annotated datasets. Many studies have attempted to tackle these challenges by developing more accurate NR-IQA models, often employing complex and computationally expensive networks, or by bridging the domain gap between various distortions to enhance performance on test datasets. In our work, we improve the performance of a generic lightweight NR-IQA model by introducing a novel augmentation strategy that boosts its performance by almost 28\%. This augmentation strategy enables the network to better discriminate between different distortions in various parts of the image by zooming in and out. Additionally, the inclusion of test-time augmentation further enhances performance, making our lightweight network's results comparable to the current state-of-the-art models, simply through the use of augmentations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Vista3D: Unravel the 3D Darkside of a Single Image MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion Efficient Low-Resolution Face Recognition via Bridge Distillation Enhancing Few-Shot Classification without Forgetting through Multi-Level Contrastive Constraints NVLM: Open Frontier-Class Multimodal LLMs
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1