{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/distill-dbdgan-knowledge-distillation-and","title":"Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur Detection","arxiv_id":null,"date":"2023-02-01","proceeding":"ACM Transactions on Multimedia Computing, Communications, and Applications 2023 2","authors":["Sankaraganesh Jonna","Moushumi Medhi","Rajiv Ranjan Sahay"],"abstract":"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.","url_abs":"https://dl.acm.org/doi/10.1145/3557897","url_pdf":"https://dl.acm.org/doi/pdf/10.1145/3557897","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"distill-dbdgan-knowledge-distillation-and","repo_url":"https://github.com/Moushumi9medhi/Distill-DBDGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"defocus-blur-detection","task_name":"Defocus Blur Detection"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/defocus-blur-detection-on-cuhk","task":"Defocus Blur Detection","dataset":"CUHK","model":"Distill-DBDGAN","rank_in_archive_order":2,"of":2,"metrics":{"Mean absolute error":"0.044"},"uses_additional_data":false},{"leaderboard":"/sota/defocus-blur-detection-on-dut","task":"Defocus Blur Detection","dataset":"DUT","model":"Distill-DBDGAN","rank_in_archive_order":1,"of":1,"metrics":{"Mean absolute error":"0.071"},"uses_additional_data":false},{"leaderboard":"/sota/defocus-blur-detection-on-szu-blur-detection","task":"Defocus Blur Detection","dataset":"SZU blur detection","model":"Distill-DBDGAN","rank_in_archive_order":1,"of":1,"metrics":{"Mean absolute error":"0.065"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}