{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T19:29:32Z","timestamp":1772566172951,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2024,2,1]]},"DOI":"10.1587\/transinf.2023edp7114","type":"journal-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T22:14:54Z","timestamp":1706739294000},"page":"201-211","source":"Crossref","is-referenced-by-count":4,"title":["Content-Adaptive Optimization Framework for Universal Deep Image Compression"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Koki","family":"TSUBOTA","sequence":"first","affiliation":[{"name":"Dept. of Information and Communication Engineering, The University of Tokyo"}]},{"given":"Kiyoharu","family":"AIZAWA","sequence":"additional","affiliation":[{"name":"Dept. of Information and Communication Engineering, The University of Tokyo"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] G.K. Wallace, \u201cThe jpeg still picture compression standard,\u201d IEEE Transactions on Consumer Electronics, vol.38, no.1, pp.xviii-xxxiv, Feb. 1992. 10.1109\/30.125072","DOI":"10.1109\/30.125072"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] A. Skodras, C. Christopoulos, and T. Ebrahimi, \u201cThe jpeg 2000 still image compression standard,\u201d IEEE Signal Processing Magazine, vol.18, no.5, pp.36-58, Sept. 2001. 10.1109\/79.952804","DOI":"10.1109\/79.952804"},{"key":"3","unstructured":"[3] F. Bellard, \u201cBpg image format.\u201d https:\/\/bellard.org\/bpg\/."},{"key":"4","unstructured":"[4] B. Bross, J. Chen, S. Liu, and Y.K. Wang, \u201cVersatile video coding (draft 10).\u201d JVET-T2001, 2020."},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] Z. Guo, Z. Zhang, R. Feng, and Z. Chen, \u201cCausal contextual prediction for learned image compression,\u201d IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol.32, no.4, pp.2329-2341, 2022. 10.1109\/tcsvt.2021.3089491","DOI":"10.1109\/TCSVT.2021.3089491"},{"key":"6","unstructured":"[6] Y. Zhu, Y. Yang, and T. Cohen, \u201cTransformer-based transform coding,\u201d International Conference on Learning Representations (ICLR), Virtual, April 2022."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] R. Zou, C. Song, and Z. Zhang, \u201cThe devil is in the details: Window-based attention for image compression,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), USA, pp.17492-17501, June 2022. 10.1109\/cvpr52688.2022.01697","DOI":"10.1109\/CVPR52688.2022.01697"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] M.J. Wilber, C. Fang, H. Jin, A. Hertzmann, J. Collomosse, and S. Belongie, \u201cBam! the behance artistic media dataset for recognition beyond photography,\u201d IEEE International Conference on Computer Vision (ICCV), Italy, pp.1211-1220, Oct. 2017. 10.1109\/iccv.2017.136","DOI":"10.1109\/ICCV.2017.136"},{"key":"9","unstructured":"[9] J. Campos, S. Meierhans, A. Djelouah, and C. Schroers, \u201cContent adaptive optimization for neural image compression,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), USA, June 2019."},{"key":"10","unstructured":"[10] Y.H. Lam, A. Zare, c. Aytekin, F. Cricri, J. Lainema, E. Aksu, and M.M. Hannuksela, \u201cCompressing weight-updates for image artifacts removal neural networks,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2019."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] Y.-H. Lam, A. Zare, F. Cricri, J. Lainema, and M.M. Hannuksela, \u201cEfficient adaptation of neural network filter for video compression,\u201d ACM Multimedia (ACMMM), Virtual, pp.358-366, Oct. 2020. 10.1145\/3394171.3413536","DOI":"10.1145\/3394171.3413536"},{"key":"12","unstructured":"[12] T. van Rozendaal, I.A. Huijben, and T. Cohen, \u201cOverfitting for fun and profit: Instance-adaptive data compression,\u201d International Conference on Learning Representations (ICLR), Virtual, May 2021."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] N. Zou, H. Zhang, F. Cricri, H.R. Tavakoli, J. Lainema, M. Hannuksela, E. Aksu, and E. Rahtu, \u201c<i>L<\/i><sup>2<\/sup><i>C<\/i>-learning to learn to compress,\u201d IEEE International Workshop on Multimedia Signal Processing (MMSP), Virtual, pp.1-6, Sept. 2020. 10.1109\/mmsp48831.2020.9287069","DOI":"10.1109\/MMSP48831.2020.9287069"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] N. Zou, H. Zhang, F. Cricri, R.G. Youvalari, H.R. Tavakoli, J. Lainema, E. Aksu, M. Hannuksela, and E. Rahtu, \u201cAdaptation and attention for neural video coding,\u201d IEEE International Symposium on Multimedia (ISM), Italy, pp.240-244, Nov. 2021. 10.1109\/ism52913.2021.00047","DOI":"10.1109\/ISM52913.2021.00047"},{"key":"15","unstructured":"[15] Y. Yang, R. Bamler, and S. Mandt, \u201cImproving inference for neural image compression,\u201d Annual Conference on Neural Information Processing System (NeurIPS), Virtual, pp.573-584, Dec. 2020."},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] G.E. Hinton and D. van Camp, \u201cKeeping the neural networks simple by minimizing the description length of the weights,\u201d Annual Conference on Computational Learning Theory (COLT), USA, pp.5-13, July 1993. 10.1145\/168304.168306","DOI":"10.1145\/168304.168306"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] C.S. Wallace, \u201cClassification by minimum-message-length inference,\u201d International Conference on Computing and Information (ICCI), Canada, pp.72-81, May 1990. 10.1007\/3-540-53504-7_63","DOI":"10.1007\/3-540-53504-7_63"},{"key":"18","unstructured":"[18] N. Houlsby, A. Giurgiu, S. Jastrzebski, B. Morrone, Q. de Laroussilhe, A. Gesmundo, M. Attariyan, and S. Gelly, \u201cParameter-efficient transfer learning for nlp,\u201d International Conference on Machine Learning (ICML), USA, pp.2790-2799, June 2019."},{"key":"19","unstructured":"[19] W.-H. Li, X. Liu, and H. Bilen, \u201cCross-domain few-shot learning with task-specific adapters,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), USA, pp.7161-7170, June 2022. 10.1109\/cvpr52688.2022.00702"},{"key":"20","unstructured":"[20] S.A. Rebuffi, H. Bilen, and A. Vedaldi, \u201cLearning multiple visual domains with residual adapters,\u201d Annual Conference on Neural Information Processing System (NeurIPS), USA, pp.506-516, Dec. 2017."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] Y.-L. Sung, J. Cho, and M. Bansal, \u201cVl-adapter: Parameter-efficient transfer learning for vision-and-language tasks,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), USA, pp.5227-5237, June 2022. 10.1109\/cvpr52688.2022.00516","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"22","unstructured":"[22] E.K. Company., \u201cKodak lossless true color image suite (photocd pcd0992).\u201d http:\/\/r0k.us\/graphics\/kodak\/, 1993."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] K. Tsubota, H. Akutsu, and K. Aizawa, \u201cUniversal deep image compression via content-adaptive optimization with adapters,\u201d IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp.2529-2538, Jan. 2023. 10.1109\/wacv56688.2023.00256","DOI":"10.1109\/WACV56688.2023.00256"},{"key":"24","unstructured":"[24] J. Ball\u00e9, V. Laparra, and E.P. Simoncelli, \u201cEnd-to-end optimized image compression,\u201d International Conference on Learning Representations (ICLR), France, April 2017."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte, and L.V. Gool, \u201cConditional probability models for deep image compression,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), USA, pp.4394-4402, June 2018. 10.1109\/cvpr.2018.00462","DOI":"10.1109\/CVPR.2018.00462"},{"key":"26","unstructured":"[26] D. Minnen, J. Ball\u00e9, and G. Toderici, \u201cJoint autoregressive and hierarchical priors for learned image compression,\u201d Annual Conference on Neural Information Processing System (NeurIPS), Canada, pp.10794-10803, Dec. 2018."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] D. Minnen and S. Singh, \u201cChannel-wise autoregressive entropy models for learned image compression,\u201d IEEE International Conference on Image Processing (ICIP), Virtual, pp.3339-3343, Sept. 2020. 10.1109\/icip40778.2020.9190935","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] Z. Cheng, H. Sun, M. Takeuchi, and J. Katto, \u201cLearned image compression with discretized gaussian mixture likelihoods and attention modules,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, pp.7936-7945, June 2020. 10.1109\/cvpr42600.2020.00796","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"29","unstructured":"[29] G. Toderici, L. Theis, N. Johnston, E. Agustsson, F. Mentzer, J. Ball\u00e9, W. Shi, and R. Timofte, \u201cClic 2020: Challenge on learned image compression.\u201d http:\/\/compression.cc, 2020."},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, and L. Fei-Fei, \u201cImagenet large scale visual recognition challenge,\u201d International Journal of Computer Vision (IJCV), vol.115, no.3, pp.211-252, 2015. 10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"31","unstructured":"[31] N. Asuni and A. Giachetti, \u201cTestimages: a large-scale archive for testing visual devices and basic image processing algorithms,\u201d Smart Tools and Apps for Graphics-Eurographics Italian Chapter Conference (STAG), Italy, pp.63-70, Sept. 2014."},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] E. Agustsson and R. Timofte, \u201cNtire 2017 challenge on single image super-resolution: Dataset and study,\u201d IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), USA, pp.1122-1131, July 2017. 10.1109\/cvprw.2017.150","DOI":"10.1109\/CVPRW.2017.150"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] J.-H. Kim, J.-H. Choi, J. Chang, and J.-S. Lee, \u201cEfficient deep learning-based lossy image compression via asymmetric autoencoder and pruning,\u201d IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Virtual, pp.2063-2067, May 2020. 10.1109\/icassp40776.2020.9053102","DOI":"10.1109\/ICASSP40776.2020.9053102"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] S.-A. Rebuffi, A. Vedaldi, and H. Bilen, \u201cEfficient parametrization of multi-domain deep neural networks,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), USA, pp.8119-8127, June 2018. 10.1109\/cvpr.2018.00847","DOI":"10.1109\/CVPR.2018.00847"},{"key":"35","unstructured":"[35] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, L. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Annual Conference on Neural Information Processing System (NeurIPS), USA, pp.5998-6008, Dec. 2017."},{"key":"36","unstructured":"[36] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, \u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp.4171-4186, June 2019."},{"key":"37","unstructured":"[37] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P.J. Liu, \u201cExploring the limits of transfer learning with a unified text-to-text transformer,\u201d Journal of Machine Learning Research (JMLR), vol.21, no.140, pp.1-67, 2020."},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] E. Ben Zaken, Y. Goldberg, and S. Ravfogel, \u201cBitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models,\u201d Annual Meeting of the Association for Computational Linguistics (ACL), Dublin, Ireland, pp.1-9, May 2022. 10.18653\/v1\/2022.acl-short.1","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"39","unstructured":"[39] J. He, C. Zhou, X. Ma, T. Berg-Kirkpatrick, and G. Neubig, \u201cTowards a unified view of parameter-efficient transfer learning,\u201d International Conference on Learning Representations (ICLR), Virtual, April 2022."},{"key":"40","unstructured":"[40] R. Karimi Mahabadi, J. Henderson, and S. Ruder, \u201cCompacter: Efficient low-rank hypercomplex adapter layers,\u201d Annual Conference on Neural Information Processing System (NeurIPS), ed. M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J.W. Vaughan, Virtual, pp.1022-1035, Dec. 2021."},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] D. Guo, A. Rush, and Y. Kim, \u201cParameter-efficient transfer learning with diff pruning,\u201d Annual Meeting of the Association for Computational Linguistics (ACL), Virtual, pp.4884-4896, Aug. 2021. 10.18653\/v1\/2021.acl-long.378","DOI":"10.18653\/v1\/2021.acl-long.378"},{"key":"42","unstructured":"[42] P.K. Mudrakarta, M. Sandler, A. Zhmoginov, and A.G. Howard, \u201cK for the price of 1: Parameter-efficient multi-task and transfer learning,\u201d International Conference on Learning Representations (ICLR), USA, May 2019."},{"key":"43","doi-asserted-by":"crossref","unstructured":"[43] R. Karimi Mahabadi, S. Ruder, M. Dehghani, and J. Henderson, \u201cParameter-efficient multi-task fine-tuning for transformers via shared hypernetworks,\u201d Annual Meeting of the Association for Computational Linguistics (ACL), Virtual, pp.565-576, Aug. 2021. 10.18653\/v1\/2021.acl-long.47","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"44","unstructured":"[44] J. Ball\u00e9, V. Laparra, and E.P. Simoncelli, \u201cDensity modeling of images using a generalized normalization transformation,\u201d International Conference on Learning Representations (ICLR), USA, May 2016."},{"key":"45","doi-asserted-by":"crossref","unstructured":"[45] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, pp.770-778, June 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"46","unstructured":"[46] J. Ball\u00e9, D. Minnen, S. Singh, S.J. Hwang, and N. Johnston, \u201cVariational image compression with a scale hyperprior,\u201d International Conference on Learning Representations (ICLR), Canada, April 2018."},{"key":"47","unstructured":"[47] J. Lee, S. Cho, and S.K. Beack, \u201cContext-adaptive entropy model for end-to-end optimized image compression,\u201d International Conference on Learning Representations (ICLR), USA, May 2019."},{"key":"48","doi-asserted-by":"publisher","unstructured":"[48] K. Tsubota and K. Aizawa, \u201cComprehensive comparisons of uniform quantization in deep image compression,\u201d IEEE Access, vol.11, pp.4455-4465, 2023. 10.1109\/access.2023.3236086","DOI":"10.1109\/ACCESS.2023.3236086"},{"key":"49","unstructured":"[49] I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, \u201cBinarized neural networks,\u201d Annual Conference on Neural Information Processing System (NeurIPS), Spain, pp.4107-4115, Dec. 2016."},{"key":"50","unstructured":"[50] J. B\u00e9gaint, F. Racap\u00e9, S. Feltman, and A. Pushparaja, \u201cCompressai: a pytorch library and evaluation platform for end-to-end compression research,\u201d arXiv, Nov. 2020."},{"key":"51","doi-asserted-by":"publisher","unstructured":"[51] A. Kuznetsova, H. Rom, N. Alldrin, J. Uijlings, I. Krasin, J. Pont-Tuset, S. Kamali, S. Popov, M. Malloci, A. Kolesnikov, T. Duerig, and V. Ferrari, \u201cThe open images dataset v4,\u201d International Journal of Computer Vision (IJCV), vol.128, no.7, pp.1956-1981, 2020. 10.1007\/s11263-020-01316-z","DOI":"10.1007\/s11263-020-01316-z"},{"key":"52","unstructured":"[52] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d International Conference on Learning Representations (ICLR), USA, May 2015."},{"key":"53","unstructured":"[53] \u201cVvc official test model vtm.\u201d https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/VVCSoftware_VTM\/-\/tags\/VTM-14.0."},{"key":"54","unstructured":"[54] G. Bj\u00f8ntegaard, \u201cCalculation of average psnr differences between rd-curves.\u201d ITU-T VCEG-M33, 2001."},{"key":"55","doi-asserted-by":"crossref","unstructured":"[55] X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang, \u201cMoment matching for multi-source domain adaptation,\u201d IEEE\/CVF International Conference on Computer Vision (ICCV), Korea, pp.1406-1415, Oct. 2019. 10.1109\/iccv.2019.00149","DOI":"10.1109\/ICCV.2019.00149"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/2\/E107.D_2023EDP7114\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,3]],"date-time":"2024-02-03T04:17:46Z","timestamp":1706933866000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/2\/E107.D_2023EDP7114\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023edp7114","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,1]]},"article-number":"2023EDP7114"}}