{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:28:58Z","timestamp":1772166538218,"version":"3.50.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA277839"],"award-info":[{"award-number":["R01CA277839"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Image Video Proc."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper presents a study on the computational complexity of coding for machines, with a focus on image coding for classification. We first conduct a comprehensive set of experiments to analyze the size of the encoder (which encodes images to bitstreams), the size of the decoder (which decodes bitstreams and predicts class labels), and their impact on the rate\u2013accuracy trade-off in compression for classification. Through empirical investigation, we demonstrate a complementary relationship between the encoder size and the decoder size, i.e., it is better to employ a large encoder with a small decoder and vice versa. Motivated by this relationship, we introduce a feature compression-based method for efficient image compression for classification. By compressing features at various layers of a neural network-based image classification model, our method achieves adjustable rate, accuracy, and encoder (or decoder) size using a single model. Experimental results on ImageNet classification show that our method achieves competitive results with existing methods while being much more flexible. The code will be made publicly available.<\/jats:p>","DOI":"10.1186\/s13640-024-00652-1","type":"journal-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T12:02:57Z","timestamp":1729598577000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Balancing the encoder and decoder complexity in image compression for classification"],"prefix":"10.1186","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7948-4356","authenticated-orcid":false,"given":"Zhihao","family":"Duan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Adnan Faisal","family":"Hossain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangpeng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"652_CR1","doi-asserted-by":"crossref","unstructured":"Choi, H. & Baji\u0107, I.\u00a0V. Deep feature compression for collaborative object detection. In: Proceedings of the IEEE international conference on image processing 3743\u20133747 (2018)","DOI":"10.1109\/ICIP.2018.8451100"},{"key":"652_CR2","doi-asserted-by":"publisher","first-page":"8680","DOI":"10.1109\/TIP.2020.3016485","volume":"29","author":"L Duan","year":"2020","unstructured":"L. Duan, J. Liu, W. Yang, T. Huang, W. Gao, Video coding for machines: a paradigm of collaborative compression and intelligent analytics. IEEE Trans. Image Process. 29, 8680\u20138695 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"652_CR3","doi-asserted-by":"crossref","unstructured":"Matsubara, Y., Yang, R., Levorato, M. & Mandt, S. Supervised compression for resource-constrained edge computing systems. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision 923\u2013933 (2022)","DOI":"10.1109\/WACV51458.2022.00100"},{"key":"652_CR4","doi-asserted-by":"crossref","unstructured":"Azizian, B. & Baji\u0107, I.\u00a0V. Privacy-preserving feature coding for machines. Picture coding symposium 205\u2013209 (2022)","DOI":"10.1109\/PCS56426.2022.10018066"},{"key":"652_CR5","unstructured":"Chen, W.-N., Song, D., Ozgur, A. & Kairouz, P. Privacy amplification via compression: Achieving the optimal privacy-accuracy-communication trade-off in distributed mean estimation. arXiv preprint arXiv:2304.01541 (2023)"},{"key":"652_CR6","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/IOTM.001.2200152","volume":"5","author":"N Shlezinger","year":"2022","unstructured":"N. Shlezinger, I.V. Baji\u0107, Collaborative inference for ai-empowered IoT devices. IEEE Internet of Things Mag. 5, 92\u201398 (2022)","journal-title":"IEEE Internet of Things Mag."},{"key":"652_CR7","doi-asserted-by":"publisher","first-page":"21916","DOI":"10.1109\/JIOT.2022.3182313","volume":"9","author":"LD Chamain","year":"2022","unstructured":"L.D. Chamain, S. Qi, Z. Ding, End-to-end image classification and compression with variational autoencoders. IEEE Internet of Things J. 9, 21916\u201321931 (2022)","journal-title":"IEEE Internet of Things J."},{"key":"652_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J. et\u00a0al. Imagenet: A large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"652_CR9","first-page":"14014","volume":"34","author":"Y Dubois","year":"2021","unstructured":"Y. Dubois, B. Bloem-Reddy, K. Ullrich, C.J. Maddison, Lossy compression for lossless prediction. Adv. Neural Inf. Process. Syst. 34, 14014\u201314028 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"652_CR10","doi-asserted-by":"crossref","unstructured":"Harell, A., De\u00a0Andrade, A. & Baji\u0107, I.\u00a0V. Rate-distortion in image coding for machines. Picture coding symposium 199\u2013203 (2022)","DOI":"10.1109\/PCS56426.2022.10018035"},{"key":"652_CR11","doi-asserted-by":"crossref","unstructured":"Harell, A. et\u00a0al. Rate-distortion theory in coding for machines and its application. arXiv preprint arXiv:2305.17295 (2023)","DOI":"10.1109\/PCS56426.2022.10018035"},{"key":"652_CR12","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/JBHI.2020.2995473","volume":"25","author":"A Doulah","year":"2021","unstructured":"A. Doulah, T. Ghosh, D. Hossain, M.H. Imtiaz, E. Sazonov, automatic ingestion monitor version 2\u2014a novel wearable device for automatic food intake detection and passive capture of food images. IEEE J. Biomed. Health Inf. 25, 568\u2013576 (2021)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"652_CR13","doi-asserted-by":"crossref","unstructured":"Singh, S. et\u00a0al. End-to-end learning of compressible features. In: Proceedings of the IEEE international conference on image processing 3349\u20133353 (2020)","DOI":"10.1109\/ICIP40778.2020.9190860"},{"key":"652_CR14","doi-asserted-by":"crossref","unstructured":"Shao, J. & Zhang, J. Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems. In: Proceedings of the IEEE international conference on communications workshops 1\u20136 (2020)","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"652_CR15","doi-asserted-by":"publisher","first-page":"3934","DOI":"10.1109\/TCSVT.2021.3107716","volume":"32","author":"S Suzuki","year":"2022","unstructured":"S. Suzuki et al., Deep feature compression using spatio-temporal arrangement toward collaborative intelligent world. IEEE Trans. Circ. Syst. Video Technol. 32, 3934\u20133946 (2022)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"652_CR16","doi-asserted-by":"crossref","unstructured":"Datta, P., Ahuja, N., Somayazulu, V.\u00a0S. & Tickoo, O. A low-complexity approach to rate-distortion optimized variable bit-rate compression for split DNN computing. In: Proceedings of the international conference on pattern recognition 182\u2013188 (2022)","DOI":"10.1109\/ICPR56361.2022.9956232"},{"key":"652_CR17","volume-title":"Elem. Inf. Theory","author":"TM Cover","year":"2006","unstructured":"T.M. Cover, J.A. Thomas, Elem. Inf. Theory (John Wiley & Sons Inc, 2006)"},{"key":"652_CR18","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S. & Johnston, N. Variational image compression with a scale hyperprior. In: International conference on learning representations (2018)"},{"key":"652_CR19","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1109\/JSTSP.2020.3034501","volume":"15","author":"J Ball\u00e9","year":"2021","unstructured":"J. Ball\u00e9 et al., Nonlinear transform coding. IEEE J. Select. Top. Signal Process. 15, 339\u2013353 (2021)","journal-title":"IEEE J. Select. Top. Signal Process."},{"key":"652_CR20","unstructured":"Dosovitskiy, A. et\u00a0al. An image is worth 16x16 words: Transformers for image recognition at scale. In: International conference on learning representations (2021)"},{"key":"652_CR21","unstructured":"Krizhevsky, A., Hinton, G. et\u00a0al. Learning multiple layers of features from tiny images (2009)"},{"key":"652_CR22","unstructured":"Kingma, D.\u00a0P. & Ba, J. Adam: A method for stochastic optimization. In: International conference on learning representations (2015)"},{"key":"652_CR23","unstructured":"Steiner, A.\u00a0P. et\u00a0al. How to train your vit? data, augmentation, and regularization in vision transformers. Transactions on Machine Learning Research (2022)"},{"key":"652_CR24","unstructured":"Ba, J.\u00a0L., Kiros, J.\u00a0R. & Hinton, G.\u00a0E. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"652_CR25","unstructured":"Zhu, Y., Yang, Y. & Cohen, T. Transformer-based transform coding. In: International conference on learning representations (2022)"},{"key":"652_CR26","unstructured":"Qian, Y., Sun, X., Lin, M., Tan, Z. & Jin, R. Entroformer: A transformer-based entropy model for learned image compression. In: International conference on learning representations (2022)"},{"key":"652_CR27","doi-asserted-by":"crossref","unstructured":"Duan, Z., Lu, M., Ma, Z. & Zhu, F. Lossy image compression with quantized hierarchical vaes. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision 198\u2013207 (2023)","DOI":"10.1109\/WACV56688.2023.00028"},{"key":"652_CR28","unstructured":"Bengio, Y., L\u00e9onard, N. & Courville, A. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"652_CR29","unstructured":"Theis, L., Shi, W., Cunningham, A. & Husz\u00e1r, F. Lossy image compression with compressive autoencoders. In: International conference on learning representations (2017)"},{"key":"652_CR30","first-page":"573","volume":"33","author":"Y Yang","year":"2020","unstructured":"Y. Yang, R. Bamler, S. Mandt, Improving inference for neural image compression. Adv. Neural Inf. Process. Syst. 33, 573\u2013584 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"652_CR31","first-page":"3920","volume":"139","author":"Z Guo","year":"2021","unstructured":"Z. Guo, Z. Zhang, R. Feng, Z. Chen, Soft then hard: rethinking the quantization in neural image compression. Proc. Int. Conf. Mach. Learn. 139, 3920\u20133929 (2021)","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"652_CR32","first-page":"10794","volume":"31","author":"D Minnen","year":"2018","unstructured":"D. Minnen, J. Ball\u00e9, G. Toderici, Joint autoregressive and hierarchical priors for learned image compression. Adv. Neural Inf. Process. Syst. 31, 10794\u201310803 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"652_CR33","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"J. Ho, A. Jain, P. Abbeel, Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"652_CR34","doi-asserted-by":"crossref","unstructured":"Choi, Y., El-Khamy, M. & Lee, J. Variable rate deep image compression with a conditional autoencoder. In: Proceedings of the IEEE\/CVF international conference on computer vision 3146\u20133154 (2019)","DOI":"10.1109\/ICCV.2019.00324"},{"key":"652_CR35","doi-asserted-by":"crossref","unstructured":"Chen, T. & Ma, Z. Variable bitrate image compression with quality scaling factors. In: IEEE international conference on acoustics, speech and signal processing 2163\u20132167 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053885"},{"key":"652_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"652_CR37","first-page":"8748","volume":"139","author":"A Radford","year":"2021","unstructured":"A. Radford et al., Learning transferable visual models from natural language supervision. Proc. Int. Conf. Mach. Learn. 139, 8748\u20138763 (2021)","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"652_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z. et\u00a0al. A convnet for the 2020s. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 11966\u201311976 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"652_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z. et\u00a0al. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"652_CR40","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Rawlekar, S., Garg, S., Erkip, E. & Wang, Y. Feature compression for rate constrained object detection on the edge. In: Proceedings of the IEEE international conference on multimedia information processing and retrieval 1\u20136 (2022)","DOI":"10.1109\/MIPR54900.2022.00008"},{"key":"652_CR41","doi-asserted-by":"crossref","unstructured":"Duan, Z. & Zhu, F. Efficient feature compression for edge-cloud systems. Picture coding symposium 187\u2013191 (2022)","DOI":"10.1109\/PCS56426.2022.10018075"},{"key":"652_CR42","first-page":"4569","volume":"45","author":"Z Hu","year":"2023","unstructured":"Z. Hu et al., FVC: an end-to-end framework towards deep video compression in feature space. IEEE Trans Pattern Anal Mach Intell 45, 4569\u20134585 (2023)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"652_CR43","doi-asserted-by":"publisher","unstructured":"Isik, B. & Weissman, T. Lossy compression of noisy data for private and data-efficient learning. IEEE J. Select. Areas Inf. Theory 3(4), 815-823 (2023). https:\/\/doi.org\/10.1109\/JSAIT.2023.3260720","DOI":"10.1109\/JSAIT.2023.3260720"},{"key":"652_CR44","doi-asserted-by":"crossref","unstructured":"Hu, Y., Yang, S., Yang, W., Duan, L.-Y. & Liu, J. Towards coding for human and machine vision: a scalable image coding approach. In: Proceedings of the IEEE international conference on multimedia and expo 1\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102750"},{"key":"652_CR45","doi-asserted-by":"publisher","first-page":"2739","DOI":"10.1109\/TIP.2022.3160602","volume":"31","author":"H Choi","year":"2022","unstructured":"H. Choi, I.V. Baji\u0107, Scalable image coding for humans and machines. IEEE Trans. Image Process. 31, 2739\u20132754 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"652_CR46","doi-asserted-by":"crossref","unstructured":"Brandenburg, J. et\u00a0al. Towards fast and efficient vvc encoding. In: IEEE international workshop on multimedia signal processing 1\u20136 (2020)","DOI":"10.1109\/MMSP48831.2020.9287093"},{"key":"652_CR47","doi-asserted-by":"publisher","first-page":"3765","DOI":"10.1109\/TCSVT.2021.3072204","volume":"31","author":"F Bossen","year":"2021","unstructured":"F. Bossen, K. S\u00fchring, A. Wieckowski, S. Liu, VVC complexity and software implementation analysis. IEEE Trans. Circ. Syst. Video Technol. 31, 3765\u20133778 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"652_CR48","doi-asserted-by":"crossref","unstructured":"Vijayaratnam, M., Milovanovi\u0107, M., Cagnazzo, M., Tartaglione, E. & Valenzise, G. Unified measures for the rate-distortion-latency trade-off. In: IEEE international conference on visual communications and image processing 1\u20135 (2023)","DOI":"10.1109\/VCIP59821.2023.10402790"},{"key":"652_CR49","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","volume":"31","author":"B Bross","year":"2021","unstructured":"B. Bross et al., Overview of the versatile video coding (VVC) standard and its applications. IEEE Trans. Circ. Syst. Video Technol. 31, 3736\u20133764 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"652_CR50","doi-asserted-by":"crossref","unstructured":"Wieckowski, A. et\u00a0al. Vvenc: An open and optimized vvc encoder implementation. In: IEEE international conference on multimedia & expo workshops 1\u20132 (2021)","DOI":"10.1109\/ICMEW53276.2021.9455944"},{"key":"652_CR51","unstructured":"Tishby, N., Pereira, F.\u00a0C. & Bialek, W. The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"key":"652_CR52","unstructured":"Alemi, A.\u00a0A., Fischer, I., Dillon, J.\u00a0V. & Murphy, K. Deep variational information bottleneck. In: International conference on learning representations (2017)"},{"key":"652_CR53","unstructured":"Federici, M., Dutta, A., Forr\u00e9, P., Kushman, N. & Akata, Z. Learning robust representations via multi-view information bottleneck. In: International conference on learning representations (2020)"},{"key":"652_CR54","unstructured":"Xu, Y., Zhao, S., Song, J., Stewart, R. & Ermon, S. A theory of usable information under computational constraints. In: International conference on learning representations (2020)"},{"key":"652_CR55","unstructured":"Kleinman, M., Achille, A., Idnani, D. & Kao, J. Usable information and evolution of optimal representations during training. In: International conference on learning representations (2021)"},{"key":"652_CR56","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"652_CR57","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et\u00a0al. Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"652_CR58","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/MMUL.2023.3245919","volume":"30","author":"J Ascenso","year":"2023","unstructured":"J. Ascenso, E. Alshina, T. Ebrahimi, The JPEG AI standard: providing efficient human and machine visual data consumption. IEEE MultiMedia 30, 100\u2013111 (2023)","journal-title":"IEEE MultiMedia"},{"key":"652_CR59","doi-asserted-by":"crossref","unstructured":"M\u00fcller, S.\u00a0G. & Hutter, F. Trivialaugment: Tuning-free yet state-of-the-art data augmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision 754\u2013762 (2021)","DOI":"10.1109\/ICCV48922.2021.00081"}],"container-title":["EURASIP Journal on Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-024-00652-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13640-024-00652-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-024-00652-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T12:04:28Z","timestamp":1729598668000},"score":1,"resource":{"primary":{"URL":"https:\/\/jivp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13640-024-00652-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,22]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["652"],"URL":"https:\/\/doi.org\/10.1186\/s13640-024-00652-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4002168\/v1","asserted-by":"object"}]},"ISSN":["1687-5281"],"issn-type":[{"value":"1687-5281","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,22]]},"assertion":[{"value":"29 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We hereby declare that there are no known financial or non-financial competing interest that influence the work reported in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"38"}}