{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:44:02Z","timestamp":1772905442527,"version":"3.50.1"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"2s","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p>Defocus blur detection (DBD) aims to segment the blurred regions from a given image affected by defocus blur. It is a crucial pre-processing step for various computer vision tasks. With the increasing popularity of small mobile devices, there is a need for a computationally efficient method to detect defocus blur accurately. We propose an efficient defocus blur detection method that estimates the probability of each pixel being focused or blurred in resource-constraint devices. Despite remarkable advances made by the recent deep learning-based methods, they still suffer from several challenges such as background clutter, scale sensitivity, indistinguishable low-contrast focused regions from out-of-focus blur, and especially high computational cost and memory requirement. To address the first three challenges, we develop a novel deep network that efficiently detects blur map from the input blurred image. Specifically, we integrate multi-scale features in the deep network to resolve the scale ambiguities and simultaneously modeled the non-local structural correlations in the high-level blur features. To handle the last two issues, we eventually frame our DBD algorithm to perform knowledge distillation by transferring information from the larger teacher network to a compact student network. All the networks are adversarially trained in an end-to-end manner to enforce higher order consistencies between the output and the target distributions. Experimental results demonstrate the state-of-the-art performance of the larger teacher network, while our proposed lightweight DBD model imitates the output of the teacher network without significant loss in accuracy. The codes, pre-trained model weights, and the results will be made publicly available.<\/jats:p>","DOI":"10.1145\/3557897","type":"journal-article","created":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T11:44:23Z","timestamp":1661168663000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur Detection"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4929-4516","authenticated-orcid":false,"given":"Sankaraganesh","family":"Jonna","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9069-8833","authenticated-orcid":false,"given":"Moushumi","family":"Medhi","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0820-0616","authenticated-orcid":false,"given":"Rajiv Ranjan","family":"Sahay","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,17]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"571","volume-title":"Computer Graphics Forum","author":"Bae Soonmin","year":"2007","unstructured":"Soonmin Bae and Fr\u00e9do Durand. 2007. Defocus magnification. In Computer Graphics Forum, Vol. 26. 571\u2013579."},{"key":"e_1_3_2_3_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV\u201918) Workshops","author":"Carvalho Marcela","year":"2018","unstructured":"Marcela Carvalho, Bertrand Le Saux, Pauline Trouv\u00e9-Peloux, Andr\u00e9s Almansa, and Fr\u00e9d\u00e9ric Champagnat. 2018. Deep depth from defocus: How can defocus blur improve 3D estimation using dense neural networks? In Proceedings of the European Conference on Computer Vision (ECCV\u201918) Workshops."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_5_2","first-page":"747","volume-title":"Proceedings of the European Conference Computer Vision (ECCV\u201920)","volume":"12358","author":"Cun X.","year":"2020","unstructured":"X. Cun and C. M. Pun. 2020. Defocus blur detection via depth distillation. In Proceedings of the European Conference Computer Vision (ECCV\u201920), Vol. 12358. 747\u2013763."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_7_2","first-page":"596","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Golestaneh S. A.","year":"2017","unstructured":"S. A. Golestaneh and L. J. Karam. 2017. Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917). 596\u2013605."},{"key":"e_1_3_2_8_2","first-page":"2672","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems (NeurIPS\u201914)","author":"Goodfellow I.","year":"2014","unstructured":"I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. 2014. Generative adversarial nets. In Proceedings of the Conference on Advances in Neural Information Processing Systems (NeurIPS\u201914). 2672\u20132680."},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Wenliang Guo Xiao Xiao Yilong Hui Wenming Yang and Amir Sadovnik. 2021. Heterogeneous attention nested U-shaped network for blur detection. IEEE Signal Process. Lett. 29 (2021) 140\u2013144.","DOI":"10.1109\/LSP.2021.3128375"},{"key":"e_1_3_2_10_2","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS\u201917), Vol. 30.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS\u201917)"},{"key":"e_1_3_2_11_2","first-page":"7132","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918)","author":"Hu J.","year":"2018","unstructured":"J. Hu, L. Shen, and G. Sun. 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918). 7132\u20137141."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.01.041"},{"key":"e_1_3_2_13_2","first-page":"31","volume-title":"Proceedings of the International Conference on Image Analysis and Signal Processing","author":"Jin-Yu Zhang","year":"2009","unstructured":"Zhang Jin-Yu, Chen Yan, and Huang Xian-Xiang. 2009. Edge detection of images based on improved Sobel operator and genetic algorithms. In Proceedings of the International Conference on Image Analysis and Signal Processing. 31\u201335."},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201919)","author":"Jolicoeur-Martineau Alexia","year":"2019","unstructured":"Alexia Jolicoeur-Martineau. 2019. The relativistic discriminator: A key element missing from standard GAN. In Proceedings of the International Conference on Learning Representations (ICLR\u201919)."},{"key":"e_1_3_2_15_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201915)","author":"Kingma Diederick P.","year":"2015","unstructured":"Diederick P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR\u201915)."},{"key":"e_1_3_2_16_2","first-page":"1620","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS\u201919)","author":"Li Boyi","year":"2019","unstructured":"Boyi Li, Felix Wu, Kilian Q. Weinberger, and Serge J. Belongie. 2019. Positional normalization. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS\u201919). 1620\u20131632."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065171"},{"key":"e_1_3_2_18_2","unstructured":"Zinan Lin Vyas Sekar and Giulia Fanti. 2020. Why spectral normalization stabilizes GANs: Analysis and improvements. Advances in Neural Information Processing Systems (NeurIPS) 34 (2020) 9652\u20139638."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2847421"},{"key":"e_1_3_2_20_2","first-page":"2813","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV\u201917)","author":"Mao X.","year":"2017","unstructured":"X. Mao, Q. Li, H. Xie, R. Y. K. Lau, Z. Wang, and S. P. Smolley. 2017. Least squares generative adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV\u201917). 2813\u20132821."},{"issue":"12","key":"e_1_3_2_21_2","doi-asserted-by":"crossref","first-page":"2947","DOI":"10.1109\/TPAMI.2018.2872043","article-title":"On the effectiveness of least squares generative adversarial networks","volume":"41","author":"Mao X.","year":"2019","unstructured":"X. Mao, Q. Li, H. Xie, R. Y. K. Lau, Z. Wang, and S. P. Smolley. 2019. On the effectiveness of least squares generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41, 12 (2019), 2947\u20132960.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_22_2","article-title":"Conditional generative adversarial nets","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv:1411.1784. Retrieved from https:\/\/arxiv.org\/abs\/1411.1784.","journal-title":"arXiv:1411.1784"},{"key":"e_1_3_2_23_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Miyato Takeru","year":"2018","unstructured":"Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. 2018. Spectral normalization for generative adversarial networks. In Proceedings of the International Conference on Learning Representations (ICLR\u201918)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.735812"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2472478"},{"key":"e_1_3_2_26_2","first-page":"2760","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Park J.","year":"2017","unstructured":"J. Park, Y. W. Tai, D. Cho, and I. S. Kweon. 2017. A unified approach of multi-scale deep and hand-crafted features for defocus estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917). 2760\u20132769."},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201916)","author":"Radford Alec","year":"2016","unstructured":"Alec Radford, Luke Metz, and Soumith Chintala. 2016. Unsupervised representation learning with deep convolutional generative adversarial networks. In Proceedings of the International Conference on Learning Representations (ICLR\u201916), Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_28_2","first-page":"234","volume-title":"Proceedings of the Annual Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI\u201915)","author":"Ronneberger O.","year":"2015","unstructured":"O. Ronneberger, P. Fischer, and T. Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the Annual Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI\u201915). 234\u2013241."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","first-page":"2965","DOI":"10.1109\/CVPR.2014.379","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201914)","author":"Shi J.","year":"2014","unstructured":"J. Shi, L. Xu, and J. Jia. 2014. Discriminative blur detection features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201914). 2965\u20132972."},{"key":"e_1_3_2_31_2","first-page":"657","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915)","author":"Shi J.","year":"2015","unstructured":"J. Shi, L. Xu, and J. Jia. 2015. Just noticeable defocus blur detection and estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915). 657\u2013665."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.068"},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201919)","author":"Tan M.","year":"2019","unstructured":"M. Tan and Q. V. Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning (ICML\u201919)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985541"},{"key":"e_1_3_2_35_2","article-title":"DeFusionNET: Defocus blur detection via recurrently fusing and refining discriminative multi-scale deep features","author":"Tang C.","year":"2022","unstructured":"C. Tang, X. Liu, X. Zheng, W. Li, J. Xiong, L. Wang, A. Zomaya, and A. Longo. 2022. DeFusionNET: Defocus blur detection via recurrently fusing and refining discriminative multi-scale deep features. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2 (2022), 955\u2013968.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_36_2","first-page":"12063","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Tang Chang","year":"2020","unstructured":"Chang Tang, Xinwang Liu, Xinzhong Zhu, En Zhu, Kun Sun, Pichao Wang, Lizhe Wang, and Albert Zomaya. 2020. R \\(^2\\) MRF: Defocus blur detection via recurrently refining multi-scale residual features. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 12063\u201312070."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2611608"},{"key":"e_1_3_2_38_2","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201919)","author":"Tang Chang","year":"2019","unstructured":"Chang Tang, Xinzhong Zhu, Xinwang Liu, Lizhe Wang, and Albert Zomaya. 2019. DeFusionNET: Defocus blur detection via recurrently fusing and refining multi-scale deep features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201919)."},{"key":"e_1_3_2_39_2","first-page":"3684","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918)","author":"Yang M.","year":"2018","unstructured":"M. Yang, K. Yu, C. Zhang, Z. Li, and K. Yang. 2018. DenseASPP for semantic segmentation in street scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918). 3684\u20133692."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2528042"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2881830"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.107996"},{"key":"e_1_3_2_43_2","first-page":"617","volume-title":"Proceedings of the European Conference Computer Vision (ECCV\u201920)","author":"Zhang Ning","year":"2020","unstructured":"Ning Zhang and Junchi Yan. 2020. Rethinking the defocus blur detection problem and a real-time deep DBD model. In Proceedings of the European Conference Computer Vision (ECCV\u201920). 617\u2013632."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3084101"},{"key":"e_1_3_2_45_2","first-page":"6933","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201921)","author":"Zhao Wenda","year":"2021","unstructured":"Wenda Zhao, Cai Shang, and Huchuan Lu. 2021. Self-generated defocus blur detection via dual adversarial discriminators. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201921). 6933\u20136942."},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918)","author":"Zhao Wenda","year":"2018","unstructured":"Wenda Zhao, Fan Zhao, Dong Wang, and Huchuan Lu. 2018. Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918)."},{"key":"e_1_3_2_47_2","first-page":"1884","article-title":"Defocus blur detection via multi-stream bottom-top-bottom network","author":"Zhao W.","year":"2019","unstructured":"W. Zhao, F. Zhao, D. Wang, and H. Lu. 2019. Defocus blur detection via multi-stream bottom-top-bottom network. IEEE Trans. Pattern Anal. Mach. Intell. 42, 8 (2019), 1884\u20131897.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_48_2","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201919)","author":"Zhao Wenda","year":"2019","unstructured":"Wenda Zhao, Bowen Zheng, Qiuhua Lin, and Huchuan Lu. 2019. Enhancing diversity of defocus blur detectors via cross-ensemble network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201919)."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3557897","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3557897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:40Z","timestamp":1750186960000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3557897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":47,"journal-issue":{"issue":"2s","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1145\/3557897"],"URL":"https:\/\/doi.org\/10.1145\/3557897","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"2022-01-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}