{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T02:47:06Z","timestamp":1748314026363},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T00:00:00Z","timestamp":1672790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T00:00:00Z","timestamp":1672790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s00521-022-08067-7","type":"journal-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T09:03:27Z","timestamp":1672823007000},"page":"7697-7718","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["TransMCGC: a recast vision transformer for small-scale image classification tasks"],"prefix":"10.1007","volume":"35","author":[{"given":"Jian-Wen","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Rong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei-Shan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao-Li","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi-Da","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Jie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,4]]},"reference":[{"issue":"1","key":"8067_CR1","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1113\/jphysiol.1962.sp006837","volume":"160","author":"DH Hubel","year":"1962","unstructured":"Hubel DH, Wiesel TN (1962) Receptive fields, binocular interaction and functional architecture in the cat\u2019s visual cortex. J Physiol 160(1):106\u2013154","journal-title":"J Physiol"},{"issue":"11","key":"8067_CR2","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"8067_CR3","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Commun ACM 60:84\u201390","journal-title":"Commun ACM"},{"key":"8067_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the 31st AAAI conference on artificial intelligence, 4\u20139 Feb 2017, San Francisco, California, USA, pp 4278\u20134284","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"8067_CR5","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8067_CR6","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85\u2013117","journal-title":"Neural Netw"},{"key":"8067_CR7","doi-asserted-by":"crossref","unstructured":"Scherer D, M\u00fcller AC, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: Proceedings of artificial neural networks\u2014ICANN 2010\u201420th international conference, Thessaloniki, Greece, 15\u201318 Sept 2010, Part III. Lecture notes in computer science, vol 6354, pp 92\u2013101","DOI":"10.1007\/978-3-642-15825-4_10"},{"key":"8067_CR8","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Proceedings of computer vision\u2014ECCV 2014\u201413th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Part I. Lecture notes in computer science, vol 8689, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"2","key":"8067_CR9","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3934\/mfc.2018008","volume":"1","author":"Z Qin","year":"2018","unstructured":"Qin Z, Yu F, Liu C, Chen X (2018) How convolutional neural networks see the world\u2014a survey of convolutional neural network visualization methods. Math Found Comput 1(2):149\u2013180","journal-title":"Math Found Comput"},{"key":"8067_CR10","doi-asserted-by":"publisher","first-page":"11905","DOI":"10.1007\/s00521-021-05863-5","volume":"33","author":"M Cadoni","year":"2021","unstructured":"Cadoni M, Lagorio A, Khellat-Kihel S, Grosso E (2021) On the correlation between human fixations, handcrafted and CNN features. Neural Comput Appl 33:11905\u201311922","journal-title":"Neural Comput Appl"},{"key":"8067_CR11","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick RB, Gupta AK, He K (2018) Non-local neural networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"8067_CR12","doi-asserted-by":"crossref","unstructured":"Zhao H, Jia J, Koltun V (2020) Exploring self-attention for image recognition. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10073\u201310082","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"8067_CR13","doi-asserted-by":"crossref","unstructured":"Srinivas A, Lin T-Y, Parmar N, Shlens J, Abbeel P, Vaswani A (2021) Bottleneck transformers for visual recognition. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 16514\u201316524","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"8067_CR14","first-page":"1","volume":"1","author":"W Wang","year":"2020","unstructured":"Wang W, Cui Y, Li G, Jiang C, Deng S (2020) A self-attention-based destruction and construction learning fine-grained image classification method for retail product recognition. Neural Comput Appl 1:1\u201310","journal-title":"Neural Comput Appl"},{"key":"8067_CR15","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"8067_CR16","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, vol 1 (Long and Short Papers), pp 4171\u20134186"},{"key":"8067_CR17","doi-asserted-by":"crossref","unstructured":"de\u00a0la Rosa J, P\u00e9rez \u00c1, Sisto MD, Hern\u00e1ndez L, D\u00edaz A, Ros S, Gonz\u00e1lez-Blanco E (2021) Transformers analyzing poetry: multilingual metrical pattern prediction with transfomer-based language models. Neural Comput Appl","DOI":"10.1007\/s00521-021-06692-2"},{"key":"8067_CR18","doi-asserted-by":"crossref","unstructured":"Bhowmick RS, Ganguli I, Sil J (2022) Character-level inclusive transformer architecture for information gain in low resource code-mixed language. Neural Comput Appl","DOI":"10.1007\/s00521-022-06983-2"},{"key":"8067_CR19","unstructured":"Chen M, Radford A, Child R, Wu J, Jun H, Luan D, Sutskever I (2020) Generative pretraining from pixels. In: Proceedings of the 37th international conference on machine learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol 119, pp 1691\u20131703"},{"key":"8067_CR20","unstructured":"Parmar N, Vaswani A, Uszkoreit J, Kaiser L, Shazeer N, Ku A, Tran D (2018) Image transformer. In: International conference on machine learning, pp 4055\u20134064. PMLR"},{"key":"8067_CR21","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: International conference on learning representations"},{"key":"8067_CR22","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhang Y, Liu Y, Wang Z, Coleman S, Kerr D (2022) Tf-sod: a novel transformer framework for salient object detection. Neural Comput Appl","DOI":"10.1007\/s00521-022-07069-9"},{"key":"8067_CR23","doi-asserted-by":"crossref","unstructured":"Yuan K, Guo S, Liu Z, Zhou A, Yu F, Wu W (2021) Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 579\u2013588","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"8067_CR24","unstructured":"d\u2019Ascoli S, Touvron H, Leavitt ML, Morcos AS, Biroli G, Sagun L (2021) Convit: improving vision transformers with soft convolutional inductive biases. In: Proceedings of the 38th international conference on machine learning, ICML 2021, 18\u201324 July 2021, Virtual Event, vol 139, pp 2286\u20132296"},{"key":"8067_CR25","unstructured":"Xu Y, Zhang Q, Zhang J, Tao D (2021) ViTAE: Vision transformer advanced by exploring intrinsic inductive bias. In: Advances in neural information processing systems"},{"key":"8067_CR26","unstructured":"Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2021) Transformer in transformer. In: Advances in neural information processing systems"},{"key":"8067_CR27","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8067_CR28","doi-asserted-by":"crossref","unstructured":"Wang Y, Xie Y, Fan L, Hu G (2022) Stmg: swin transformer for multi-label image recognition with graph convolution network. Neural Comput Appl","DOI":"10.1007\/s00521-022-06990-3"},{"key":"8067_CR29","doi-asserted-by":"crossref","unstructured":"Heo B, Yun S, Han D, Chun S, Choe J, Oh SJ (2021) Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 11936\u201311945","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"8067_CR30","unstructured":"Cordonnier J-B, Loukas A, Jaggi M (2020) On the relationship between self-attention and convolutional layers. In: International conference on learning representations"},{"key":"8067_CR31","unstructured":"Peng G, Lu J, Li H, Mottaghi R, Kembhavi A (2021) Container: context aggregation networks. In: Advances in neural information processing systems"},{"key":"8067_CR32","unstructured":"Varma M, Prabhu NS (2021) [re]: On the relationship between self-attention and convolutional layers"},{"key":"8067_CR33","unstructured":"Xiao T, Dollar P, Singh M, Mintun E, Darrell T, Girshick R (2021) Early convolutions help transformers see better. In: Advances in neural information processing systems"},{"key":"8067_CR34","doi-asserted-by":"crossref","unstructured":"Zhang H, Dana KJ, Shi J, Zhang Z, Wang X, Tyagi A, Agrawal A (2018) Context encoding for semantic segmentation. 2018 IEEE\/CVF conference on computer vision and pattern recognition, 7151\u20137160","DOI":"10.1109\/CVPR.2018.00747"},{"key":"8067_CR35","unstructured":"Tan M, Le QV (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th international conference on machine learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA. Proceedings of machine learning research, vol 97, pp 6105\u20136114"},{"key":"8067_CR36","doi-asserted-by":"publisher","first-page":"8507","DOI":"10.1007\/s00521-019-04316-4","volume":"32","author":"Y Jiang","year":"2019","unstructured":"Jiang Y, Yang F, Zhu H, Zhou D, Zeng X (2019) Nonlinear CNN: improving CNNs with quadratic convolutions. Neural Comput Appl 32:8507\u20138516","journal-title":"Neural Comput Appl"},{"key":"8067_CR37","doi-asserted-by":"publisher","first-page":"9295","DOI":"10.1007\/s00521-019-04281-y","volume":"31","author":"J Leng","year":"2019","unstructured":"Leng J, Liu Y, Chen S (2019) Context-aware attention network for image recognition. Neural Comput Appl 31:9295\u20139305","journal-title":"Neural Comput Appl"},{"key":"8067_CR38","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H (2021) Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th international conference on machine learning, ICML 2021, 18\u201324 July 2021, virtual event. Proceedings of machine learning research, vol 139, pp 10347\u201310357"},{"key":"8067_CR39","unstructured":"Ba J, Kiros JR, Hinton GE (2016) Layer normalization. arXiv:1607.06450"},{"key":"8067_CR40","unstructured":"Hendrycks D, Gimpel K (2016) Gaussian error linear units (gelus). arXiv: Learning"},{"key":"8067_CR41","unstructured":"Wang P, Zheng W, Chen T, Wang Z (2022) Anti-oversmoothing in deep vision transformers via the fourier domain analysis: from theory to practice. In: International conference on learning representations"},{"key":"8067_CR42","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein MS, Berg AC, Fei-Fei L (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115:211\u2013252","journal-title":"Int J Comput Vision"},{"key":"8067_CR43","doi-asserted-by":"crossref","unstructured":"Pan Z, Zhuang B, Liu J, He H, Cai J (2021) Scalable vision transformers with hierarchical pooling. In: IEEE\/CVF international conference on computer vision (ICCV), pp 367\u2013376","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"8067_CR44","unstructured":"Xie J, Zeng R, Wang Q, Zhou Z, Li P (2021) So-vit: mind visual tokens for vision transformer. CoRR. arxiv:2104.10935"},{"key":"8067_CR45","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images"},{"key":"8067_CR46","doi-asserted-by":"publisher","first-page":"2014","DOI":"10.13053\/cys-18-3-2043","volume":"18","author":"G Sidorov","year":"2014","unstructured":"Sidorov G, Gelbukh A, G\u00f3mez-Adorno H, Pinto D (2014) Soft similarity and soft cosine measure: similarity of features in vector space model. Computaci\u00f3n y Sistemas 18:2014","journal-title":"Computaci\u00f3n y Sistemas"},{"key":"8067_CR47","first-page":"6","volume":"8","author":"N Kadowaki","year":"2020","unstructured":"Kadowaki N, Kishida K (2020) Empirical comparison of word similarity measures based on co-occurrence, context, and a vector space model. J Inf Sci Theory Pract 8:6\u201317","journal-title":"J Inf Sci Theory Pract"},{"key":"8067_CR48","unstructured":"Nguyen T, Raghu M, Kornblith S (2021) Do wide and deep networks learn the same things? uncovering how neural network representations vary with width and depth. In: International conference on learning representations"},{"key":"8067_CR49","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","volume":"37","author":"J Lin","year":"1991","unstructured":"Lin J (1991) Divergence measures based on the Shannon entropy. IEEE Trans Inf Theory 37:145\u2013151","journal-title":"IEEE Trans Inf Theory"},{"key":"8067_CR50","doi-asserted-by":"crossref","unstructured":"Xiao T, Li Y, Zhu J, Yu Z, Liu T (2019) Sharing attention weights for fast transformer. In: Proceedings of the 28th international joint conference on artificial intelligence, IJCAI 2019, Macao, China, August 10\u201316, 2019, pp 5292\u20135298","DOI":"10.24963\/ijcai.2019\/735"},{"key":"8067_CR51","unstructured":"Michel P, Levy O, Neubig G (2019) Are sixteen heads really better than one? In: Advances in neural information processing systems 32: annual conference on neural information processing systems 2019, NeurIPS 2019, 8\u201314 Dec 2019, Vancouver, BC, Canada, pp 14014\u201314024"},{"key":"8067_CR52","unstructured":"Dong Y, Cordonnier J, Loukas A (2021) Attention is not all you need: pure attention loses rank doubly exponentially with depth. In: Meila M, Zhang T (eds) Proceedings of the 38th international conference on machine learning, ICML 2021, 18-24 July 2021, virtual event. Proceedings of machine learning research, vol 139, pp 2793\u20132803. PMLR"},{"key":"8067_CR53","unstructured":"Shi H, GAO J, Xu H, Liang X, Li Z, Kong L, Lee SMS, Kwok J (2022) Revisiting over-smoothing in BERT from the perspective of graph. In: International conference on learning representations"},{"key":"8067_CR54","unstructured":"Huang W, Rong Y, Xu T, Sun F, Huang J (2020) Tackling over-smoothing for general graph convolutional networks. CoRR. arxiv:2008.09864"},{"key":"8067_CR55","unstructured":"Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi K, Jegelka S (2018) Representation learning on graphs with jumping knowledge networks. In: Dy JG, Krause A (eds) Proceedings of the 35th international conference on machine learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10\u201315, 2018. Proceedings of Machine Learning Research, vol 80, pp 5449\u20135458. PMLR"},{"key":"8067_CR56","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, ICML 2015, Lille, France, 6-11 July 2015. JMLR workshop and conference proceedings, vol 37, pp 448\u2013456"},{"key":"8067_CR57","doi-asserted-by":"crossref","unstructured":"Bossard L, Guillaumin M, Gool LV (2014) Food-101 - mining discriminative components with random forests. In: Computer vision\u2014ECCV 2014\u201413th European conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part VI. Lecture notes in computer science, vol 8694, pp 446\u2013461","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"8067_CR58","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: IEEE international conference on computer vision workshops, ICCV Workshops 2013, Sydney, Australia, December 1\u20138, 2013, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"8067_CR59","doi-asserted-by":"crossref","unstructured":"Cimpoi M, Maji S, Kokkinos I, Mohamed S, Vedaldi A (2014) Describing textures in the wild. In: 2014 IEEE conference on computer vision and pattern recognition, CVPR 2014, Columbus, OH, USA, 23\u201328 June 2014, pp 3606\u20133613","DOI":"10.1109\/CVPR.2014.461"},{"key":"8067_CR60","doi-asserted-by":"crossref","unstructured":"Nilsback M, Zisserman A (2008) Automated flower classification over a large number of classes. In: 6th Indian conference on computer vision, graphics & image processing, ICVGIP 2008, Bhubaneswar, India, 16\u201319 Dec 2008, pp 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"8067_CR61","doi-asserted-by":"crossref","unstructured":"Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: AAAI","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"8067_CR62","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Shlens J, Le QV (2020) Randaugment: practical automated data augmentation with a reduced search space. 2020 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW), pp 3008\u20133017","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"8067_CR63","doi-asserted-by":"crossref","unstructured":"Kornblith S, Shlens J, Le QV (2019) Do better imagenet models transfer better? In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019, pp 2661\u20132671","DOI":"10.1109\/CVPR.2019.00277"},{"key":"8067_CR64","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"},{"key":"8067_CR65","unstructured":"Tan M, Le QV (2021) Efficientnetv2: smaller models and faster training. In: Proceedings of the 38th international conference on machine learning,ICML 2021, July 18\u201324 2021, virtual event. Proceedings of machine learning research, vol 139, pp 10096\u201310106"},{"key":"8067_CR66","unstructured":"Huang Y, Cheng Y, Bapna A, Firat O, Chen D, Chen MX, Lee H, Ngiam J, Le QV, Wu Y, Chen Z (2019) Gpipe: efficient training of giant neural networks using pipeline parallelism. In: Advances in neural information processing systems 32: annual conference on neural information processing systems 2019, NeurIPS 2019, 8\u201314 Dec 2019, Vancouver, BC, Canada, pp 103\u2013112"},{"key":"8067_CR67","doi-asserted-by":"crossref","unstructured":"Kolesnikov A, Beyer L, Zhai X, Puigcerver J, Yung J, Gelly S, Houlsby N (2020) Big transfer (bit): General visual representation learning. In: ECCV","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"8067_CR68","doi-asserted-by":"crossref","unstructured":"Touvron H, Bojanowski P, Caron M, Cord M, El-Nouby A, Grave E, Joulin A, Synnaeve G, Verbeek J, J\u00e9gou H (2021) Resmlp: feedforward networks for image classification with data-efficient training. CoRR. arxiv:2105.03404 2021","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"8067_CR69","unstructured":"Tatsunami Y, Taki M (2021) Raftmlp: How much can be done without attention and with less spatial locality?"},{"key":"8067_CR70","unstructured":"Tolstikhin I, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T, Yung J, Steiner AP, Keysers D, Uszkoreit J, Lucic M, Dosovitskiy A (2021) MLP-mixer: An all-MLP architecture for vision. In: Advances in neural information processing systems"},{"key":"8067_CR71","unstructured":"Rao Y, Zhao W, Zhu Z, Lu J, Zhou J (2021) Global filter networks for image classification. In: Advances in neural information processing systems"},{"key":"8067_CR72","unstructured":"Chen C-F, Panda R, Fan Q (2022) Regionvit: Regional-to-local attention for vision transformers. In: International conference on learning representations"},{"key":"8067_CR73","doi-asserted-by":"crossref","unstructured":"Chen C, Fan Q, Panda R (2021) Crossvit: cross-attention multi-scale vision transformer for image classification. CoRR. arxiv:2103.14899 2021","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"8067_CR74","unstructured":"El-Nouby A, Touvron H, Caron M, Bojanowski P, Douze M, Joulin A, Laptev I, Neverova N, Synnaeve G, Verbeek J, Jegou H (2021) XCit: Cross-covariance image transformers. In: Advances in neural information processing systems"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08067-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-08067-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08067-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T01:52:27Z","timestamp":1679881947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-08067-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,4]]},"references-count":74,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["8067"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-08067-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,4]]},"assertion":[{"value":"7 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}