{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:26:09Z","timestamp":1763533569850,"version":"3.45.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T00:00:00Z","timestamp":1749686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100017668","name":"Key Research and Development Project of Anhui Province","doi-asserted-by":"publisher","award":["202204c06020022"],"award-info":[{"award-number":["202204c06020022"]}],"id":[{"id":"10.13039\/501100017668","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Independent Project of Key Laboratory of Agricultural Sensors, Ministry of Agriculture and Rural Affairs","award":["KLAS2023KF006"],"award-info":[{"award-number":["KLAS2023KF006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper proposes an enhanced frequency-domain knowledge distillation framework to address limitations in spatial-domain approaches, where multiple downsampling operations compromise detail preservation and conventional attention-based mechanisms fail to fully capture the global contextual information. (1) An adaptive frequency prompt module where the frequency prompt interacts with teacher frequency bands during fine-tuning to capture contextual semantic frequency. During the distillation process, the frequency prompt is used to generate a pixel-by-pixel mask to locate the pixels of interest in different frequency bands. The channel-level position-sensitive weight is designed to provide high-order spatial enhancement. (2) A feature fusion module that hierarchically fuses multilevel features to reinforce the local structure. (3) Extensive experiments demonstrate state-of-the-art performance, when the teacher\u2013student architecture is the same, achieving 1.83% and 1.03% Top-1 accuracy improvements over ReviewKD and CAT-KD on the CIFAR-100 dataset, and it also performs competitively on the Tiny-ImageNet dataset, along with a 4.5% average precision improvement for the anchor-free detector FCOS-R50 on the MS COCO dataset. The framework\u2019s effectiveness is further validated through cross-architecture evaluations, showing consistent superiority in balancing model efficiency and accuracy. This work provides new insights into frequency-aware knowledge distillation for lightweight model optimization.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf074","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T08:12:52Z","timestamp":1747123972000},"page":"1785-1797","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge distillation with adaptive frequency prompting"],"prefix":"10.1093","volume":"68","author":[{"given":"Jing","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenxiang","family":"Chi","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]},{"name":"Key Laboratory of Agricultural Sensors , Ministry of Agriculture and Rural Affairs, Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]},{"name":"Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiu","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]},{"name":"Key Laboratory of Agricultural Sensors , Ministry of Agriculture and Rural Affairs, Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]},{"name":"Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Rao","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]},{"name":"Key Laboratory of Agricultural Sensors , Ministry of Agriculture and Rural Affairs, Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]},{"name":"Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment , Anhui Agricultural University, 130, Changjiang West Road, Hefei 230036, Anhui,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,6,12]]},"reference":[{"key":"2025111901220980500_ref1","doi-asserted-by":"publisher","first-page":"14495","DOI":"10.1038\/s41598-023-41545-z","article-title":"Utilizing convolutional neural networks to classify monkeypox skin lesions","volume":"13","author":"Eliwa","year":"2023","journal-title":"Sci Rep"},{"key":"2025111901220980500_ref2","doi-asserted-by":"publisher","first-page":"6727","DOI":"10.3390\/s23156727","article-title":"Innovative hybrid approach for masked face recognition using pretrained mask detection and segmentation, robust PCA, and KNN classifier","volume":"23","author":"Eman","year":"2023","journal-title":"Sensors"},{"key":"2025111901220980500_ref3","doi-asserted-by":"publisher","first-page":"1352935","DOI":"10.3389\/fpls.2024.1352935","article-title":"Semantic segmentation of microbial alterations based on SegFormer","volume":"15","author":"Elmessery","year":"2024","journal-title":"Front Plant Sci"},{"key":"2025111901220980500_ref4","first-page":"1389","article-title":"Channel pruning for accelerating very deep neural networks","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"He","year":"2017"},{"key":"2025111901220980500_ref5","first-page":"1","article-title":"Quantized neural networks: training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2018","journal-title":"J Mach Learn Res"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"2025111901220980500_ref6"},{"key":"2025111901220980500_ref7","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int J Comput Vision"},{"article-title":"Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer","year":"2016","author":"Zagoruyko","key":"2025111901220980500_ref8"},{"key":"2025111901220980500_ref9","first-page":"1641","article-title":"Frequenecy domain compact 3D convolutional neural networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2020"},{"key":"2025111901220980500_ref10","first-page":"12464","article-title":"Wavelet knowledge distillation: towards efficient image-to-image translation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2022"},{"key":"2025111901220980500_ref11","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1109\/TCSVT.2008.918843","article-title":"Invariant image watermarking based on statistical features in the low-frequency domain","volume":"18","author":"Xiang","year":"2008","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2025111901220980500_ref12","first-page":"11953","article-title":"Decoupled knowledge distillation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2022"},{"key":"2025111901220980500_ref13","first-page":"5008","article-title":"Distilling knowledge via knowledge review","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2021"},{"key":"2025111901220980500_ref14","first-page":"3967","article-title":"Relational knowledge distillation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Park","year":"2019"},{"key":"2025111901220980500_ref15","first-page":"16296","article-title":"Wasserstein contrastive representation distillation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2021"},{"article-title":"Contrastive representation distillation","year":"2019","author":"Tian","key":"2025111901220980500_ref16"},{"article-title":"FitNets: hints for thin deep nets","year":"2014","author":"Romero","key":"2025111901220980500_ref17"},{"key":"2025111901220980500_ref18","first-page":"268","article-title":"Learning deep representations with probabilistic knowledge transfer","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Passalis","year":"2018"},{"key":"2025111901220980500_ref19","first-page":"1365","article-title":"Similarity-preserving knowledge distillation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Tung","year":"2019"},{"key":"2025111901220980500_ref20","first-page":"9163","article-title":"Variational information distillation for knowledge transfer","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ahn","year":"2019"},{"key":"2025111901220980500_ref21","first-page":"1921","article-title":"A comprehensive overhaul of feature distillation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Heo","year":"2019"},{"key":"2025111901220980500_ref22","first-page":"11868","article-title":"Class attention transfer based knowledge distillation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Guo","year":"2023"},{"key":"2025111901220980500_ref23","first-page":"65299","article-title":"Knowledge diffusion for distillation","volume-title":"Advances in Neural Information Processing Systems","author":"Huang","year":"2023"},{"key":"2025111901220980500_ref24","first-page":"4643","article-title":"Focal and global knowledge distillation for detectors","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yang","year":"2022"},{"key":"2025111901220980500_ref25","first-page":"16520","article-title":"CrossKD: cross-head knowledge distillation for object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2024"},{"key":"2025111901220980500_ref26","first-page":"13352","article-title":"Posterior distillation sampling","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Koo","year":"2024"},{"key":"2025111901220980500_ref27","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"2025111901220980500_ref28"},{"key":"2025111901220980500_ref29","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"Zagoruyko","year":"2016"},{"key":"2025111901220980500_ref30","first-page":"116","article-title":"ShuffleNet v2: practical guidelines for efficient CNN architecture design","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Ma","year":"2018"},{"article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"2025111901220980500_ref31"},{"key":"2025111901220980500_ref32","first-page":"5213","article-title":"Distilling object detectors with feature richness","volume-title":"Advances in Neural Information Processing Systems","author":"Zhixing","year":"2021"},{"key":"2025111901220980500_ref33","first-page":"5311","article-title":"Channel-wise knowledge distillation for dense prediction","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Shu","year":"2021"},{"key":"2025111901220980500_ref34","article-title":"Improve object detection with feature-based knowledge distillation: towards accurate and efficient detectors","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2020"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/11\/1785\/63480184\/bxaf074.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/11\/1785\/63480184\/bxaf074.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:22:22Z","timestamp":1763533342000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/11\/1785\/8161173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,12]]},"references-count":34,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,6,12]]},"published-print":{"date-parts":[[2025,11,13]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf074","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,6,12]]}}}