{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T01:37:15Z","timestamp":1772156235401,"version":"3.50.1"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Innovation and Technology Commission [InnoHK Project Centre For Intelligent Multidimensional Data Analysis Limited (CIMDA)]"},{"name":"General Research Fund of the Research Grant Council of Hong Kong","award":["11203220"],"award-info":[{"award-number":["11203220"]}]},{"name":"Innovation and Technology Fund (ITF) Project","award":["GHP\/044\/21SZ"],"award-info":[{"award-number":["GHP\/044\/21SZ"]}]},{"name":"City University of Hong Kong (CityU) Strategic Interdisciplinary Research","award":["7020055"],"award-info":[{"award-number":["7020055"]}]},{"name":"Hong Kong Research Grants Council Early Career Scheme","award":["21200522"],"award-info":[{"award-number":["21200522"]}]},{"name":"Chow Sang Sang Group Research Fund","award":["DON-RMG (Project 9229161)"],"award-info":[{"award-number":["DON-RMG (Project 9229161)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3416873","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T20:15:22Z","timestamp":1719260122000},"page":"4377-4390","source":"Crossref","is-referenced-by-count":2,"title":["Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2862-5542","authenticated-orcid":false,"given":"Yibing","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6709-0261","authenticated-orcid":false,"given":"Chris Xing","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8723-8112","authenticated-orcid":false,"given":"Haoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-959X","authenticated-orcid":false,"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. 26th Annu. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref5","first-page":"2178","article-title":"Generalizing from several related classification tasks to a new unlabeled sample","volume-title":"Proc. NeurIPS","author":"Blanchard"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/1610075.1610094"},{"key":"ref7","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019","journal-title":"arXiv:1907.02893"},{"key":"ref8","article-title":"Gradient matching for domain generalization","volume-title":"Proc. ICLR","author":"Shi"},{"key":"ref9","first-page":"18347","article-title":"Fishr: Invariant gradient variances for out-of-distribution generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rame"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2758199"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227457"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref15","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266169"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.609"},{"key":"ref18","first-page":"6447","article-title":"Domain generalization via model-agnostic learning of semantic features","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dou"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_40"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00948"},{"key":"ref22","article-title":"Contrastive syn-to-real generalization","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref23","first-page":"7313","article-title":"Domain generalization using causal matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mahajan"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00029"},{"key":"ref25","article-title":"Optimal representations for covariate shift","volume-title":"Proc. ICLR","author":"Ruan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907375117"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref28","article-title":"Concept evolution in deep learning training: A unified interpretation framework and discoveries","author":"Park","year":"2022","journal-title":"arXiv:2203.16475"},{"key":"ref29","first-page":"3387","article-title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","volume-title":"Proc. NeurIPS","author":"Nguyen"},{"key":"ref30","article-title":"Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks","author":"Nguyen","year":"2016","journal-title":"arXiv:1602.03616"},{"key":"ref31","article-title":"Object detectors emerge in deep scene CNNs","volume-title":"Proc. ICLR","author":"Zhou"},{"key":"ref32","article-title":"Natural language descriptions of deep visual features","volume-title":"Proc. ICLR","author":"Hernandez"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114858"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157441"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11682"},{"key":"ref41","first-page":"59","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","article-title":"Improve unsupervised domain adaptation with mixup training","author":"Yan","year":"2020","journal-title":"arXiv:2001.00677"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref45","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krueger"},{"key":"ref46","article-title":"Adaptive risk minimization: Learning to adapt to domain shift","author":"Zhang","year":"2020","journal-title":"arXiv:2007.02931"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266172"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_14"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00642"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00087"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_45"},{"key":"ref53","first-page":"5339","article-title":"Generalizing to unseen domains via adversarial data augmentation","volume-title":"Proc. NeurIPS","author":"Volpi"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3253211"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475496"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00696"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00903"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934659"},{"key":"ref59","first-page":"2673","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV)","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_18"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330579"},{"issue":"3","key":"ref64","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1145\/3490489","article-title":"NPC: Neuron path coverage via characterizing decision logic of deep neural networks","volume":"31","author":"Xie","year":"2022","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"ref65","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref66","article-title":"In search of lost domain generalization","volume-title":"Proc. ICLR","author":"Gulrajani"},{"key":"ref67","first-page":"1746","article-title":"Automated synthetic-to-real generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref69","article-title":"Distributionally robust neural networks","volume-title":"Proc. ICLR","author":"Sagawa"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"issue":"2","key":"ref71","first-page":"2:1","article-title":"Domain generalization by marginal transfer learning","volume":"22","author":"Blanchard","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref72","article-title":"Learning explanations that are hard to vary","volume-title":"Proc. ICLR","author":"Parascandolo"},{"key":"ref73","article-title":"Sand-mask: An enhanced gradient masking strategy for the discovery of invariances in domain generalization","volume-title":"Proc. ICML UDL Workshop","author":"Shahtalebi"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00858"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00168"},{"key":"ref76","article-title":"Understanding dimensional collapse in contrastive self-supervised learning","volume-title":"Proc. ICLR","author":"Jing"},{"key":"ref77","first-page":"6225","article-title":"Learning towards minimum hyperspherical energy","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref81","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Wang"},{"issue":"13","key":"ref82","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"James","year":"2017","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref83","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00823"},{"key":"ref85","article-title":"VisDA: The visual domain adaptation challenge","author":"Peng","year":"2017","journal-title":"arXiv:1710.06924"},{"key":"ref86","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref87","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref88","first-page":"22405","article-title":"SWAD: Domain generalization by seeking flat minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cha"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00711"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.208"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611768"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref95","first-page":"26658","article-title":"Rotated multi-scale interaction network for referring remote sensing image segmentation","volume-title":"Proc. CVPR","author":"Liu"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27969"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10570068.pdf?arnumber=10570068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T06:35:40Z","timestamp":1723271740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3416873","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}