The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
심층 이미지 압축은 자연 이미지에서 JPEG와 같은 기존 코덱보다 더 나은 성능을 발휘하지만 학습 기반 접근 방식으로는 문제에 직면합니다. 즉, 도메인 외부 이미지의 경우 압축 성능이 크게 저하됩니다. 이 문제를 조사하기 위해 자연 이미지, 선 그리기 및 만화와 같은 임의의 영역에서 이미지를 압축하는 범용 심층 이미지 압축이라는 새로운 작업을 소개합니다. 또한, 우리는 이 작업을 해결하기 위해 콘텐츠 적응형 최적화 프레임워크를 제안합니다. 이 프레임워크는 사전 훈련과 테스트 간의 도메인 격차를 해결하기 위해 테스트 중에 사전 훈련된 압축 모델을 각 대상 이미지에 적용합니다. 각 입력 이미지에 대해 모델의 디코더에 어댑터를 삽입하고 이미지당 전송된 어댑터 매개변수를 사용하여 비율 왜곡 측면에서 인코더와 어댑터 매개변수에 의해 추출된 잠재 표현을 최적화합니다. 제안된 범용 심층 압축의 평가를 달성하기 위해 자연 이미지, 선 그리기, 만화 및 벡터 아트의 네 가지 영역의 비압축 이미지가 포함된 벤치마크 데이터 세트를 구축했습니다. 제안한 방법을 비적응형 압축 방법과 기존 적응형 압축 방법과 비교한 결과, 제안한 방법이 더 나은 성능을 보였다. 우리의 코드와 데이터 세트는 https://github.com/kktsubota/universal-dic에서 공개적으로 제공됩니다.
Koki TSUBOTA
The University of Tokyo
Kiyoharu AIZAWA
The University of Tokyo
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Koki TSUBOTA, Kiyoharu AIZAWA, "Content-Adaptive Optimization Framework for Universal Deep Image Compression" in IEICE TRANSACTIONS on Information,
vol. E107-D, no. 2, pp. 201-211, February 2024, doi: 10.1587/transinf.2023EDP7114.
Abstract: While deep image compression performs better than traditional codecs like JPEG on natural images, it faces a challenge as a learning-based approach: compression performance drastically decreases for out-of-domain images. To investigate this problem, we introduce a novel task that we call universal deep image compression, which involves compressing images in arbitrary domains, such as natural images, line drawings, and comics. Furthermore, we propose a content-adaptive optimization framework to tackle this task. This framework adapts a pre-trained compression model to each target image during testing for addressing the domain gap between pre-training and testing. For each input image, we insert adapters into the decoder of the model and optimize the latent representation extracted by the encoder and the adapter parameters in terms of rate-distortion, with the adapter parameters transmitted per image. To achieve the evaluation of the proposed universal deep compression, we constructed a benchmark dataset containing uncompressed images of four domains: natural images, line drawings, comics, and vector arts. We compare our proposed method with non-adaptive and existing adaptive compression methods, and the results show that our method outperforms them. Our code and dataset are publicly available at https://github.com/kktsubota/universal-dic.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7114/_p
부
@ARTICLE{e107-d_2_201,
author={Koki TSUBOTA, Kiyoharu AIZAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Content-Adaptive Optimization Framework for Universal Deep Image Compression},
year={2024},
volume={E107-D},
number={2},
pages={201-211},
abstract={While deep image compression performs better than traditional codecs like JPEG on natural images, it faces a challenge as a learning-based approach: compression performance drastically decreases for out-of-domain images. To investigate this problem, we introduce a novel task that we call universal deep image compression, which involves compressing images in arbitrary domains, such as natural images, line drawings, and comics. Furthermore, we propose a content-adaptive optimization framework to tackle this task. This framework adapts a pre-trained compression model to each target image during testing for addressing the domain gap between pre-training and testing. For each input image, we insert adapters into the decoder of the model and optimize the latent representation extracted by the encoder and the adapter parameters in terms of rate-distortion, with the adapter parameters transmitted per image. To achieve the evaluation of the proposed universal deep compression, we constructed a benchmark dataset containing uncompressed images of four domains: natural images, line drawings, comics, and vector arts. We compare our proposed method with non-adaptive and existing adaptive compression methods, and the results show that our method outperforms them. Our code and dataset are publicly available at https://github.com/kktsubota/universal-dic.},
keywords={},
doi={10.1587/transinf.2023EDP7114},
ISSN={1745-1361},
month={February},}
부
TY - JOUR
TI - Content-Adaptive Optimization Framework for Universal Deep Image Compression
T2 - IEICE TRANSACTIONS on Information
SP - 201
EP - 211
AU - Koki TSUBOTA
AU - Kiyoharu AIZAWA
PY - 2024
DO - 10.1587/transinf.2023EDP7114
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E107-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2024
AB - While deep image compression performs better than traditional codecs like JPEG on natural images, it faces a challenge as a learning-based approach: compression performance drastically decreases for out-of-domain images. To investigate this problem, we introduce a novel task that we call universal deep image compression, which involves compressing images in arbitrary domains, such as natural images, line drawings, and comics. Furthermore, we propose a content-adaptive optimization framework to tackle this task. This framework adapts a pre-trained compression model to each target image during testing for addressing the domain gap between pre-training and testing. For each input image, we insert adapters into the decoder of the model and optimize the latent representation extracted by the encoder and the adapter parameters in terms of rate-distortion, with the adapter parameters transmitted per image. To achieve the evaluation of the proposed universal deep compression, we constructed a benchmark dataset containing uncompressed images of four domains: natural images, line drawings, comics, and vector arts. We compare our proposed method with non-adaptive and existing adaptive compression methods, and the results show that our method outperforms them. Our code and dataset are publicly available at https://github.com/kktsubota/universal-dic.
ER -