{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:42:00Z","timestamp":1777696920380,"version":"3.51.4"},"reference-count":46,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301353"],"award-info":[{"award-number":["62301353"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401383"],"award-info":[{"award-number":["62401383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62275186"],"award-info":[{"award-number":["62275186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Suzhou Science and Technology Planning Project-Industrial Fore-sight and Key Core Technology Project","award":["SYC2022140"],"award-info":[{"award-number":["SYC2022140"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Data Analysis: An International Journal"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:p>Recent deep model pruning methods predominantly focus on large-scale datasets and typically require finetuning before deployment. However, in real-world applications, pruning is often necessary for scenarios with fewer classification categories, where finetuning must be avoided to preserve the model\u2019s generalization ability. To address these challenges, we introduce a novel pruning method called Cluster-based Redundancy Elimination (CRE). Specifically, CRE represents each convolutional kernel as a point in a high-dimensional space. A distance-based strategy is then used to compute a clustering radius for each convolutional layer. Based on these radii, core point filters are selected for pruning, as they represent redundant information that can be captured by neighboring filters in the high-dimensional space. This approach eliminates the need for finetuning, thus preserving the generalization of deep models. Extensive experiments on five benchmark datasets with limited classification categories, across multiple model architectures, demonstrate the effectiveness of our method and its superiority over several state-of-the-art pruning techniques.<\/jats:p>","DOI":"10.1177\/1088467x251344924","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T03:58:01Z","timestamp":1748577481000},"page":"296-316","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Kernel clustering-based deep model pruning for few category datasets"],"prefix":"10.1177","volume":"30","author":[{"given":"Yuchen","family":"Huang","sequence":"first","affiliation":[{"name":"School of Rail Transportation, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4710-4275","authenticated-orcid":false,"given":"Jie","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Rail Transportation, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7634-3945","authenticated-orcid":false,"given":"Kangwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Rail Transportation, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Rail Transportation, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"crossref","unstructured":"Ding X Hao T Tan J et al. ResRep: lossless CNN pruning via decoupling remembering and forgetting. In: International conference on computer vision (ICCV) 2021 pp. 4490\u20134500.","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"e_1_3_4_3_2","doi-asserted-by":"crossref","unstructured":"Lin M Ji R Wang Y et al. HRank: filter pruning using high-rank feature map. In: Conference on computer vision and pattern recognition (CVPR) 2020 pp. 1526\u20131535.","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"e_1_3_4_4_2","doi-asserted-by":"crossref","unstructured":"Kirillov A Mintun E Ravi N et al. Segment anything. In: International conference on computer vision (ICCV) 2023 pp. 3992\u20134003.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_4_5_2","doi-asserted-by":"crossref","unstructured":"He K Gkioxari G Doll\u00e1r P et al. Mask R-CNN. In: International conference on computer vision (ICCV) 2017 pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_4_6_2","doi-asserted-by":"crossref","unstructured":"Iofinova E Peste A Alistarh D. Bias in pruned vision models: in-depth analysis and countermeasures. In: Conference on computer vision and pattern recognition (CVPR) 2023 pp. 24364\u201324373.","DOI":"10.1109\/CVPR52729.2023.02334"},{"key":"e_1_3_4_7_2","doi-asserted-by":"crossref","unstructured":"Zhuang X Ge Y Zheng B et al. Adversarial network pruning by filter robustness estimation. In: International conference on acoustics speech and signal processing (ICASSP) 2023 pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095291"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_4_9_2","doi-asserted-by":"crossref","unstructured":"He Y Ding Y Liu P et al. Learning filter pruning criteria for deep convolutional neural networks acceleration. In: Conference on computer vision and pattern recognition (CVPR) 2020 pp. 2006\u20132015.","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"e_1_3_4_10_2","doi-asserted-by":"crossref","unstructured":"Yu R Li A Chen CF et al. NISP: pruning networks using neuron importance score propagation. In: Conference on computer vision and pattern recognition (CVPR) 2018 pp. 9194\u20139203.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","unstructured":"Lin M Ji R Zhang Y et al. Channel pruning via automatic structure search. In: International joint conference on artificial intelligence (IJCAI) 2020 pp. 673\u2013679.","DOI":"10.24963\/ijcai.2020\/94"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2933477"},{"key":"e_1_3_4_13_2","unstructured":"Shen M Yin H Molchanov P et al. Structural pruning via latency-saliency knapsack. In: Advances in neural information processing systems (NeurIPS) 2022 pp. 1\u20138."},{"key":"e_1_3_4_14_2","doi-asserted-by":"crossref","unstructured":"Lin S Ji R Yan C et al. Towards optimal structured CNN pruning via generative adversarial learning. In: Conference on computer vision and pattern recognition (CVPR) 2019 pp. 2785\u20132794.","DOI":"10.1109\/CVPR.2019.00290"},{"key":"e_1_3_4_15_2","unstructured":"LeCun Y Denker J Solla S. Optimal brain damage. In: Advances in neural information processing systems (NeurIPS) Vol. 2 Morgan-Kaufmann 1989."},{"key":"e_1_3_4_16_2","doi-asserted-by":"crossref","unstructured":"Hou Z Qin M Sun F et al. CHEX: CHannel EXploration for CNN model compression. In: Conference on computer vision and pattern recognition (CVPR) 2022 pp. 12277\u201312288.","DOI":"10.1109\/CVPR52688.2022.01197"},{"key":"e_1_3_4_17_2","doi-asserted-by":"crossref","unstructured":"Zhang L Wang Z Dong X et al. Towards fairness-aware adversarial network pruning. In: International conference on computer vision (ICCV) 2023 pp. 5145\u20135154.","DOI":"10.1109\/ICCV51070.2023.00477"},{"key":"e_1_3_4_18_2","doi-asserted-by":"crossref","unstructured":"Peng Y Kim K Wu F et al. Structured pruning of self-supervised pre-trained models for speech recognition and understanding. In: International conference on acoustics speech and signal processing (ICASSP) 2023 pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095780"},{"key":"e_1_3_4_19_2","doi-asserted-by":"crossref","unstructured":"Zhou Z Zhou Y Jiang Z et al. An efficient method for model pruning using knowledge distillation with few samples. In: International conference on acoustics speech and signal processing (ICASSP) 2022 pp. 2515\u20132519.","DOI":"10.1109\/ICASSP43922.2022.9746024"},{"key":"e_1_3_4_20_2","doi-asserted-by":"crossref","unstructured":"Kirkpatrick J Pascanu R Rabinowitz N et al. Overcoming catastrophic forgetting in neural networks. In: National academy of sciences Vol. 114 2017 pp. 3521\u20133526.","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_4_21_2","doi-asserted-by":"crossref","unstructured":"Hu Y Yang J Chen L et al. Planning-oriented autonomous driving. In: Conference on computer vision and pattern recognition (CVPR) 2023 pp. 17853\u201317862.","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"e_1_3_4_22_2","doi-asserted-by":"crossref","unstructured":"He Y Liu P Wang Z et al. Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Conference on computer vision and pattern recognition (CVPR) 2019 pp. 4335\u20134344.","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_4_23_2","unstructured":"Li H Kadav A Durdanovic I et al. Pruning filters for efficient ConvNets. In: International conference on learning representations (ICLR) OpenReview.net 2017."},{"key":"e_1_3_4_24_2","doi-asserted-by":"crossref","unstructured":"Huang Y Liu N Che Z et al. CP3: channel pruning plug-in for point-based networks. In: Conference on computer vision and pattern recognition (CVPR) 2023 pp. 5302\u20135312.","DOI":"10.1109\/CVPR52729.2023.00513"},{"key":"e_1_3_4_25_2","doi-asserted-by":"crossref","unstructured":"Quadrianto N Sharmanska V Thomas O. Discovering fair representations in the data domain. In: Conference on computer vision and pattern recognition (CVPR) 2019 pp. 8219\u20138228.","DOI":"10.1109\/CVPR.2019.00842"},{"key":"e_1_3_4_26_2","doi-asserted-by":"crossref","unstructured":"Molchanov P Mallya A Tyree S et al. Importance estimation for neural network pruning. In: Conference on computer vision and pattern recognition (CVPR) 2019 pp. 11256\u201311264.","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_4_27_2","doi-asserted-by":"crossref","unstructured":"Bai Y Zhou H Chen R et al. g-BERT: enabling green BERT deployment on FPGA via hardware-aware hybrid pruning. In: International conference on communications 2023 pp. 1706\u20131711.","DOI":"10.1109\/ICC45041.2023.10278567"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"Xu K Wang Z Geng X et al. Efficient joint optimization of layer-adaptive weight pruning in deep neural networks. In: International conference on computer vision (ICCV) 2023 pp. 17401\u201317411.","DOI":"10.1109\/ICCV51070.2023.01600"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858232"},{"key":"e_1_3_4_30_2","doi-asserted-by":"crossref","unstructured":"Chen S Sun W Huang L. WHC: weighted hybrid criterion for filter pruning on convolutional neural networks. In: International conference on acoustics speech and signal processing (ICASSP) 2023 pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10094874"},{"key":"e_1_3_4_31_2","doi-asserted-by":"crossref","unstructured":"Duggal R Xiao C Vuduc R et al. CUP: cluster pruning for compressing deep neural networks. In: International conference on big data (big data) 2021 pp. 5102\u20135106.","DOI":"10.1109\/BigData52589.2021.9671980"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-226810"},{"key":"e_1_3_4_33_2","doi-asserted-by":"crossref","unstructured":"Deng J Dong W Socher R et al. ImageNet: a large-scale hierarchical image database. In: International conference on computer vision and pattern recognition (CVPR) 2009 pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_4_34_2","unstructured":"Simonyan K Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International conference on neural information processing systems (NeurIPS) 2014 pp. 1\u20139."},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S et al. Deep residual learning for image recognition. In: Conference on computer vision and pattern recognition (CVPR) 2016 pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_36_2","doi-asserted-by":"crossref","unstructured":"Huang G Liu Z Van Der Maaten L et al. Densely connected convolutional networks. In: Conference on computer vision and pattern recognition (CVPR) 2017 pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_4_38_2","doi-asserted-by":"crossref","unstructured":"Woo S Debnath S Hu R et al. Convnext v2: co-designing and scaling convnets with masked autoencoders. In: Conference on computer vision and pattern recognition (CVPR) 2023 pp. 16133\u201316142.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"e_1_3_4_39_2","doi-asserted-by":"crossref","unstructured":"Girshick R. Fast R-CNN. In: International conference on computer vision (ICCV) 2015 pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_4_40_2","unstructured":"Krizhevsky A Hinton G. Learning multiple layers of features from tiny images 2009."},{"key":"e_1_3_4_41_2","unstructured":"Everingham M Van Gool L Williams CKI et al. The PASCAL visual object classes (VOC) Challenge. In: International conference on computer vision (ICCV) 2012 pp. 108\u2013115."},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863"},{"key":"e_1_3_4_44_2","doi-asserted-by":"crossref","unstructured":"Sun X Shi H. Towards better structured pruning saliency by reorganizing convolution. In: Winter conference on applications of computer vision (WACV) 2024 pp. 2193\u20132203.","DOI":"10.1109\/WACV57701.2024.00220"},{"key":"e_1_3_4_45_2","unstructured":"Molchanov P Tyree S Karras T et al. Pruning convolutional neural networks for resource efficient inference. In: International conference on learning representations (ICLR) OpenReview.net 2017."},{"key":"e_1_3_4_46_2","doi-asserted-by":"crossref","unstructured":"Han X Chu Y Wang K et al. TAILOR: inter-feature distinction filter fusion pruning. In: Information sciences Vol. 665 2024 p. 120229.","DOI":"10.1016\/j.ins.2024.120229"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-55942-5"}],"container-title":["Intelligent Data Analysis: An International Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251344924","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1088467X251344924","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251344924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:19Z","timestamp":1777454479000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1088467X251344924"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1177\/1088467X251344924"],"URL":"https:\/\/doi.org\/10.1177\/1088467x251344924","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]}}}