Afsana Ahsan Jeny, Masum Shah Junayed, Md Baharul Islam
{"title":"一个有效的端到端图像压缩转换器","authors":"Afsana Ahsan Jeny, Masum Shah Junayed, Md Baharul Islam","doi":"10.1109/ICIP46576.2022.9897663","DOIUrl":null,"url":null,"abstract":"Image and video compression received significant research attention and expanded their applications. Existing entropy estimation-based methods combine with hyperprior and local context, limiting their efficacy. This paper introduces an efficient end-to-end transformer-based image compression model, which generates a global receptive field to tackle the long-range correlation issues. A hyper encoder-decoder-based transformer block employs a multi-head spatial reduction self-attention (MHSRSA) layer to minimize the computational cost of the self-attention layer and enable rapid learning of multi-scale and high-resolution features. A Casual Global Anticipation Module (CGAM) is designed to construct highly informative adjacent contexts utilizing channel-wise linkages and identify global reference points in the latent space for end-to-end rate-distortion optimization (RDO). Experimental results demonstrate the effectiveness and competitive performance of the KODAK dataset.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Efficient End-To-End Image Compression Transformer\",\"authors\":\"Afsana Ahsan Jeny, Masum Shah Junayed, Md Baharul Islam\",\"doi\":\"10.1109/ICIP46576.2022.9897663\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Image and video compression received significant research attention and expanded their applications. Existing entropy estimation-based methods combine with hyperprior and local context, limiting their efficacy. This paper introduces an efficient end-to-end transformer-based image compression model, which generates a global receptive field to tackle the long-range correlation issues. A hyper encoder-decoder-based transformer block employs a multi-head spatial reduction self-attention (MHSRSA) layer to minimize the computational cost of the self-attention layer and enable rapid learning of multi-scale and high-resolution features. A Casual Global Anticipation Module (CGAM) is designed to construct highly informative adjacent contexts utilizing channel-wise linkages and identify global reference points in the latent space for end-to-end rate-distortion optimization (RDO). Experimental results demonstrate the effectiveness and competitive performance of the KODAK dataset.\",\"PeriodicalId\":387035,\"journal\":{\"name\":\"2022 IEEE International Conference on Image Processing (ICIP)\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Conference on Image Processing (ICIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIP46576.2022.9897663\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Image Processing (ICIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIP46576.2022.9897663","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An Efficient End-To-End Image Compression Transformer
Image and video compression received significant research attention and expanded their applications. Existing entropy estimation-based methods combine with hyperprior and local context, limiting their efficacy. This paper introduces an efficient end-to-end transformer-based image compression model, which generates a global receptive field to tackle the long-range correlation issues. A hyper encoder-decoder-based transformer block employs a multi-head spatial reduction self-attention (MHSRSA) layer to minimize the computational cost of the self-attention layer and enable rapid learning of multi-scale and high-resolution features. A Casual Global Anticipation Module (CGAM) is designed to construct highly informative adjacent contexts utilizing channel-wise linkages and identify global reference points in the latent space for end-to-end rate-distortion optimization (RDO). Experimental results demonstrate the effectiveness and competitive performance of the KODAK dataset.