{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:16:32Z","timestamp":1761365792417,"version":"build-2065373602"},"reference-count":23,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Project of Gansu","award":["24JRRA388"],"award-info":[{"award-number":["24JRRA388"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Generally, the interpretability of deep neural networks is categorized into a priori and a posteriori interpretability. A priori interpretability involves improving model transparency through deliberate design prior to training. Feature disentanglement is a method for achieving a priori interpretability. Existing disentanglement methods mostly focus on semantic features, such as intrinsic and shared features. These methods distinguish between the background and the main subject, but overlook class-level features in images. To address this, we take a further step by advancing feature disentanglement to the class level. For multi-label image classification tasks, we propose a class-level feature disentanglement method. Specifically, we introduce a multi-head classifier within the feature extraction layer of the backbone network to disentangle features. Each head in this classifier corresponds to a specific class and generates independent predictions, thereby guiding the model to better leverage the intrinsic features of each class and improving multi-label classification precision. Experiments demonstrate that our method significantly enhances performance metrics across various benchmarks while simultaneously achieving a priori interpretability.<\/jats:p>","DOI":"10.3390\/fi17110486","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T01:35:11Z","timestamp":1761269711000},"page":"486","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Class-Level Feature Disentanglement for Multi-Label Image Classification"],"prefix":"10.3390","volume":"17","author":[{"given":"Yingduo","family":"Tong","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4175-5402","authenticated-orcid":false,"given":"Zhenyu","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Educational Technology, NorthWest Normal University, Lanzhou 730070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yize","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8926-2039","authenticated-orcid":false,"given":"Yonggang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,23]]},"reference":[{"key":"ref_1","unstructured":"Ayoobi, H., Potyka, N., and Toni, F. (March, January 25). ProtoArgNet: Interpretable image classification with super-prototypes and argumentation. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.procs.2020.03.179","article-title":"Segmentation and feature extraction in medical imaging: A systematic review","volume":"167","author":"Chowdhary","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., RoyChowdhury, A., and Maji, S. (2015). Bilinear CNNs for fine-grained visual recognition. arXiv.","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref_4","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., and Lerchner, A. (2017, January 24\u201326). beta-vae: Learning basic visual concepts with a constrained variational framework. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_6","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (July, January 26). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"110256","DOI":"10.1016\/j.knosys.2023.110256","article-title":"Enhancing the reliability of image classification using the intrinsic features","volume":"263","author":"Lu","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref_8","unstructured":"Zeiler, M.D., and Fergus, R. (2016, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Z\u00fcrich, Switzerland."},{"key":"ref_9","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv."},{"key":"ref_10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Proceedings of the Conference and Workshop on Neural Information Processing Systems, Long Beach, CA, USA, 4\u20139 December 2017, NeurIPS Foundation."},{"key":"ref_11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_12","unstructured":"Jain, S., and Wallace, B.C. (2019, January 2\u20137). Attention is not Explanation. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). Why Should I Trust You? Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_14","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A survey on explainable artificial intelligence (xai): Toward medical xai","volume":"32","author":"Tjoa","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Arafat, I.M., Ferdous, S.M.S., and Quarles, J. (2018, January 18\u201322). Cybersickness-provoking virtual reality alters brain signals of persons with multiple sclerosis. Proceedings of the 2018 IEEE Conference on Virtual Reality and 3D User Interfaces (VR), T\u00fcbingen\/Reutlingen, Germany.","DOI":"10.1109\/VR.2018.8446194"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dara, S., and Tumma, P. (2018, January 29\u201331). Feature extraction by using deep learning: A survey. Proceedings of the 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India.","DOI":"10.1109\/ICECA.2018.8474912"},{"key":"ref_18","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016). Infogan: Interpretable representation learning by information maximizing generative adversarial nets. Advances in Neural Information Processing Systems, Proceedings of the Conference and Workshop on Neural Information Processing Systems, Barcelona, Spain, 5\u201310 December 2016, NeurIPS Foundation."},{"key":"ref_19","unstructured":"Chen, X., Kingma, D.P., Salimans, T., Duan, Y., Dhariwal, P., Schulman, J., Sutskever, I., and Abbeel, P. (2016). Variational lossy autoencoder. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13\u201319). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_21","unstructured":"Tjoa, E., and Guan, C. (2020). New opportunities for the formal proof of computational real geometry?. arXiv."},{"key":"ref_22","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., and Lopez-Paz, D. (2019). Invariant risk minimization. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/TIV.2023.3307157","article-title":"Radar-camera fusion for object detection and semantic segmentation in autonomous driving: A comprehensive review","volume":"9","author":"Yao","year":"2023","journal-title":"IEEE Trans. Intell. Veh."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/11\/486\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:12:16Z","timestamp":1761365536000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/11\/486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,23]]},"references-count":23,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["fi17110486"],"URL":"https:\/\/doi.org\/10.3390\/fi17110486","relation":{},"ISSN":["1999-5903"],"issn-type":[{"type":"electronic","value":"1999-5903"}],"subject":[],"published":{"date-parts":[[2025,10,23]]}}}