{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T03:05:00Z","timestamp":1787972700075,"version":"build-2784847793"},"reference-count":88,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1204200"],"award-info":[{"award-number":["2023YFF1204200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z241100004224011"],"award-info":[{"award-number":["Z241100004224011"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["YSBR-116"],"award-info":[{"award-number":["YSBR-116"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441606"],"award-info":[{"award-number":["62441606"]}],"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":["62236009"],"award-info":[{"award-number":["62236009"]}],"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":["U22A20103"],"award-info":[{"award-number":["U22A20103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1016\/j.neunet.2025.107395","type":"journal-article","created":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T05:27:24Z","timestamp":1742448444000},"page":"107395","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["Enabling scale and rotation invariance in convolutional neural networks with retina like transformation"],"prefix":"10.1016","volume":"187","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5687-1839","authenticated-orcid":false,"given":"Jiahong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8994-431X","authenticated-orcid":false,"given":"Guoqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4442-7391","authenticated-orcid":false,"given":"Qiaoyi","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1111-1529","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107395_b1","article-title":"A novel deep learning architecture for agriculture land cover and land use classification from remote sensing images based on network-level fusion of self-attention architecture","author":"Albarakati","year":"2024","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.107395_b2","doi-asserted-by":"crossref","unstructured":"Altstidl, T., Nguyen, A., Schwinn, L., K\u00f6ferl, F., Mutschler, C., Eskofier, B., et al. (2023). Just a matter of scale? Reevaluating scale equivariance in convolutional neural networks. In International joint conference on neural networks (pp. 1\u20138).","DOI":"10.1109\/IJCNN54540.2023.10191724"},{"key":"10.1016\/j.neunet.2025.107395_b3","doi-asserted-by":"crossref","unstructured":"Amorim, M., Bortoloti, F., Ciarelli, P. M., de Oliveira, E., & de Souza, A. F. (2018). Analysing rotation-invariance of a log-polar transformation in convolutional neural networks. In International joint conference on neural networks (pp. 1\u20136).","DOI":"10.1109\/IJCNN.2018.8489295"},{"key":"10.1016\/j.neunet.2025.107395_b4","series-title":"Optics of the human eye","author":"Atchison","year":"2023"},{"key":"10.1016\/j.neunet.2025.107395_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.amc.2019.124594","article-title":"Scale, translation and rotation invariant wavelet local feature descriptor","volume":"363","author":"Barajas-Garcia","year":"2019","journal-title":"Applied Mathematics and Computation"},{"key":"10.1016\/j.neunet.2025.107395_b6","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1068\/p200585","article-title":"Evidence for complete translational and reflectional invariance in visual object priming","volume":"20","author":"Biederman","year":"1991","journal-title":"Perception"},{"issue":"121","key":"10.1016\/j.neunet.2025.107395_b7","article-title":"Size invariance in visual object priming","volume":"18","author":"Biederman","year":"1992","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"key":"10.1016\/j.neunet.2025.107395_b8","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1003963","article-title":"Deep neural networks rival the representation of primate it cortex for core visual object recognition","volume":"10","author":"Cadieu","year":"2014","journal-title":"PLoS Computational Biology"},{"issue":"2883","key":"10.1016\/j.neunet.2025.107395_b9","article-title":"Lpnet: Retina inspired neural network for object detection and recognition","volume":"10","author":"Cao","year":"2021","journal-title":"Electronics"},{"key":"10.1016\/j.neunet.2025.107395_b10","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107395_b11","unstructured":"Chen, F. X., Roig, G., Isik, L., Boix, X., & Poggio, T. (2017). Eccentricity dependent deep neural networks: Modeling invariance in human vision. In AAAI spring symposium series."},{"key":"10.1016\/j.neunet.2025.107395_b12","doi-asserted-by":"crossref","first-page":"2367","DOI":"10.1109\/TPAMI.2022.3166905","article-title":"Scale-aware automatic augmentations for object detection with dynamic training","volume":"45","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107395_b13","doi-asserted-by":"crossref","unstructured":"Cheng, G., Zhou, P., & Han, J. (2016). Rifd-cnn: Rotation-invariant and fisher discriminative convolutional neural networks for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2884\u20132893).","DOI":"10.1109\/CVPR.2016.315"},{"key":"10.1016\/j.neunet.2025.107395_b14","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., et al. (2017). Deformable convolutional networks. In Proceedings of the IEEE international conference on computer vision (pp. 764\u2013773).","DOI":"10.1109\/ICCV.2017.89"},{"key":"10.1016\/j.neunet.2025.107395_b15","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Li, F. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.neunet.2025.107395_b16","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.1093\/mnras\/stv632","article-title":"Rotation-invariant convolutional neural networks for galaxy morphology prediction","volume":"450","author":"Dieleman","year":"2015","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"key":"10.1016\/j.neunet.2025.107395_b17","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.neunet.2025.107395_b18","unstructured":"Esteves, C., Allen-Blanchette, C., Zhou, X., & Daniilidis, K. (2018). Polar transformer networks. In 6th international conference on learning representations. URL:."},{"key":"10.1016\/j.neunet.2025.107395_b19","doi-asserted-by":"crossref","unstructured":"Fang, Y., Jo, G. S., & Lee, C. H. (2021). Rsinet: Rotation-scale invariant network for online visual tracking. In 25th international conference on pattern recognition (pp. 4153\u20134160).","DOI":"10.1109\/ICPR48806.2021.9412862"},{"key":"10.1016\/j.neunet.2025.107395_b20","doi-asserted-by":"crossref","first-page":"11977","DOI":"10.1109\/TPAMI.2023.3275142","article-title":"Learning an invariant and equivariant network for weakly supervised object detection","volume":"45","author":"Feng","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107395_b21","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/S0042-6989(99)00134-0","article-title":"Perceptual learning in object recognition: Object specificity and size invariance","volume":"40","author":"Furmanski","year":"2000","journal-title":"Vision Research"},{"key":"10.1016\/j.neunet.2025.107395_b22","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1093\/cercor\/4.5.532","article-title":"Properties of simulated neurons from a model of primate inferior temporal cortex","volume":"4","author":"Gochin","year":"1994","journal-title":"Cerebral Cortex"},{"key":"10.1016\/j.neunet.2025.107395_b23","doi-asserted-by":"crossref","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","article-title":"Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream","volume":"35","author":"G\u00fcc\u013c\u00fc","year":"2015","journal-title":"Journal of Neuroscience"},{"key":"10.1016\/j.neunet.2025.107395_b24","first-page":"1","article-title":"A novel deep dual self-attention and bi-lstm fusion framework for parkinson\u2019s disease prediction using freezing of gait: a biometric application","author":"Habib","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2025.107395_b25","doi-asserted-by":"crossref","first-page":"1985","DOI":"10.1109\/TPAMI.2008.234","article-title":"Rotation invariant kernels and their application to shape analysis","volume":"31","author":"Hamsici","year":"2009","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1411","key":"10.1016\/j.neunet.2025.107395_b26","article-title":"Scale and translation-invariance for novel objects in human vision","volume":"10","author":"Han","year":"2020","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2025.107395_b27","unstructured":"Harris, E. W. A., Niranjan, M., & Hare, J. (2019). . Foveated convolutions: improving spatial transformer networks by modelling the retina. In Shared visual representations in human & machine intelligence workshop at neurIPS."},{"key":"10.1016\/j.neunet.2025.107395_b28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2025.107395_b29","series-title":"International conference on learning representations","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"issue":"661","key":"10.1016\/j.neunet.2025.107395_b30","article-title":"A multi-scale convolutional neural network for rotation-invariant recognition","volume":"11","author":"Hong","year":"2022","journal-title":"Electronics"},{"key":"10.1016\/j.neunet.2025.107395_b31","doi-asserted-by":"crossref","unstructured":"Hu, P., & Ramanan, D. (2017). Finding tiny faces. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 951\u2013959).","DOI":"10.1109\/CVPR.2017.166"},{"key":"10.1016\/j.neunet.2025.107395_b32","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.neunet.2025.107395_b33","series-title":"Eye, brain, and vision","author":"Hubel","year":"1995"},{"key":"10.1016\/j.neunet.2025.107395_b34","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1126\/science.1117593","article-title":"Fast readout of object identity from macaque inferior temporal cortex","volume":"310","author":"Hung","year":"2005","journal-title":"Science"},{"key":"10.1016\/j.neunet.2025.107395_b35","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448\u2013456)."},{"key":"10.1016\/j.neunet.2025.107395_b36","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1152\/jn.00394.2013","article-title":"The dynamics of invariant object recognition in the human visual system","volume":"111","author":"Isik","year":"2014","journal-title":"Journal of Neurophysiology"},{"key":"10.1016\/j.neunet.2025.107395_b37","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1152\/jn.1995.73.1.218","article-title":"Size and position invariance of neuronal responses in monkey inferotemporal cortex","volume":"73","author":"Ito","year":"1995","journal-title":"Journal of Neurophysiology"},{"key":"10.1016\/j.neunet.2025.107395_b38","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107395_b39","doi-asserted-by":"crossref","unstructured":"Jansson, Y., & Lindeberg, T. (2021). Exploring the ability of cnn s to generalise to previously unseen scales over wide scale ranges. In 25th international conference on pattern recognition (pp. 1181\u20131188).","DOI":"10.1109\/ICPR48806.2021.9413276"},{"key":"10.1016\/j.neunet.2025.107395_b40","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1007\/s10851-022-01082-2","article-title":"Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales","volume":"64","author":"Jansson","year":"2022","journal-title":"Journal of Mathematical Imaging and Vision"},{"key":"10.1016\/j.neunet.2025.107395_b41","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1109\/TPAMI.2015.2409880","article-title":"Scale and rotation invariant matching using linearly augmented trees","volume":"37","author":"Jiang","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107395_b42","series-title":"Locally scale-invariant convolutional neural networks","author":"Kanazawa","year":"2014"},{"key":"10.1016\/j.neunet.2025.107395_b43","series-title":"Cycnn: A rotation invariant CNN using polar mapping and cylindrical convolution layers","author":"Kim","year":"2020"},{"key":"10.1016\/j.neunet.2025.107395_b44","series-title":"3rd international conference on learning representations","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.neunet.2025.107395_b45","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107395_b46","doi-asserted-by":"crossref","unstructured":"Laptev, D., Savinov, N., Buhmann, J. M., & Pollefeys, M. (2016). Ti-pooling: transformation-invariant pooling for feature learning in convolutional neural networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 289\u2013297).","DOI":"10.1109\/CVPR.2016.38"},{"key":"10.1016\/j.neunet.2025.107395_b47","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2025.107395_b48","series-title":"Brain inspired computing: A systematic survey and future trends","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2025.107395_b49","unstructured":"Li, F., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In Proceedings of the IEEE\/CVF computer vision and pattern recognition workshop (pp. 178\u2013178)."},{"key":"10.1016\/j.neunet.2025.107395_b50","doi-asserted-by":"crossref","unstructured":"Li, Y., & Liu, G. (2016). Learning a scale-and-rotation correlation filter for robust visual tracking. In IEEE international conference on image processing (pp. 454\u2013458).","DOI":"10.1109\/ICIP.2016.7532398"},{"key":"10.1016\/j.neunet.2025.107395_b51","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhu, J., Hoi, S. C., Song, W., Wang, Z., & Liu, H. (2019). Robust estimation of similarity transformation for visual object tracking. In Proceedings of the AAAI conference on artificial intelligence (pp. 8666\u20138673).","DOI":"10.1609\/aaai.v33i01.33018666"},{"key":"10.1016\/j.neunet.2025.107395_b52","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.neunet.2025.107395_b53","article-title":"Non-local recurrent network for image restoration","volume":"31","author":"Liu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107395_b54","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/S0960-9822(95)00108-4","article-title":"Shape representation in the inferior temporal cortex of monkeys","volume":"5","author":"Logothetis","year":"1995","journal-title":"Current Biology"},{"key":"10.1016\/j.neunet.2025.107395_b55","doi-asserted-by":"crossref","unstructured":"Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Proceedings of the seventh IEEE international conference on computer vision (pp. 1150\u20131157).","DOI":"10.1109\/ICCV.1999.790410"},{"key":"10.1016\/j.neunet.2025.107395_b56","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.107395_b57","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007699","article-title":"Near-optimal combination of disparity across a log-polar scaled visual field","volume":"16","author":"Maiello","year":"2020","journal-title":"PLoS Computational Biology"},{"key":"10.1016\/j.neunet.2025.107395_b58","series-title":"Vision: a computational investigation into the human representation and processing of visual information","author":"Marr","year":"2010"},{"key":"10.1016\/j.neunet.2025.107395_b59","first-page":"1","article-title":"Rotation-invariant feature learning via convolutional neural network with cyclic polar coordinates convolutional layer","volume":"61","author":"Mei","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.107395_b60","doi-asserted-by":"crossref","first-page":"4325","DOI":"10.1523\/JNEUROSCI.18-11-04325.1998","article-title":"Translation-invariant orientation tuning in visual complex cells could derive from intradendritic computations","volume":"18","author":"Mel","year":"1998","journal-title":"Journal of Neuroscience"},{"key":"10.1016\/j.neunet.2025.107395_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109994","article-title":"Ric-cnn: Rotation-invariant coordinate convolutional neural network","volume":"146","author":"Mo","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107395_b62","doi-asserted-by":"crossref","first-page":"4700","DOI":"10.1523\/JNEUROSCI.13-11-04700.1993","article-title":"A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information","volume":"13","author":"Olshausen","year":"1993","journal-title":"Journal of Neuroscience"},{"key":"10.1016\/j.neunet.2025.107395_b63","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1016\/S0893-6080(97)00034-8","article-title":"Scan: A scalable neural model of covert attention","volume":"10","author":"Postma","year":"1997","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107395_b64","series-title":"Proceedings of the 26th international conference on artificial intelligence and statistics","first-page":"2460","article-title":"Deep neural networks with efficient guaranteed invariances","author":"Rath","year":"2023"},{"key":"10.1016\/j.neunet.2025.107395_b65","doi-asserted-by":"crossref","unstructured":"Remmelzwaal, L. A., Mishra, A. K., & Ellis, G. F. (2020). Human eye inspired log-polar pre-processing for neural networks. In International SAUPEC\/robMech\/PRASA conference (pp. 1\u20136).","DOI":"10.1109\/SAUPEC\/RobMech\/PRASA48453.2020.9041103"},{"key":"10.1016\/j.neunet.2025.107395_b66","doi-asserted-by":"crossref","first-page":"1716","DOI":"10.1109\/TPAMI.2022.3165730","article-title":"Equivariant wavelets: Fast rotation and translation invariant wavelet scattering transforms","volume":"45","author":"Saydjari","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107395_b67","series-title":"Uncertainty in artificial intelligence","first-page":"1749","article-title":"Probabilistic spatial transformer networks","author":"Schw\u00f6bel","year":"2022"},{"key":"10.1016\/j.neunet.2025.107395_b68","series-title":"2nd international conference on learning representations","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"Sermanet","year":"2014"},{"key":"10.1016\/j.neunet.2025.107395_b69","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.neunet.2025.107395_b70","first-page":"5751","article-title":"Log-polar space convolution layers","volume":"35","author":"Su","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107395_b71","doi-asserted-by":"crossref","first-page":"3159","DOI":"10.1111\/cogs.12684","article-title":"Gaze and the eye pupil adjust to imagined size and distance","volume":"42","author":"Sulutvedt","year":"2018","journal-title":"Cognitive Science"},{"key":"10.1016\/j.neunet.2025.107395_b72","series-title":"Proceedings of the 36th international conference on machine learning","first-page":"6086","article-title":"Equivariant transformer networks","author":"Tai","year":"2019"},{"key":"10.1016\/j.neunet.2025.107395_b73","series-title":"International conference on machine learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.neunet.2025.107395_b74","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.robot.2009.10.002","article-title":"A review of log-polar imaging for visual perception in robotics","volume":"58","author":"Traver","year":"2010","journal-title":"Robotics and Autonomous Systems"},{"issue":"5895","key":"10.1016\/j.neunet.2025.107395_b75","article-title":"Brainnet: a fusion assisted novel optimal framework of residual blocks and stacked autoencoders for multimodal brain tumor classification","volume":"14","author":"Ullah","year":"2024","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2025.107395_b76","article-title":"Do deep neural networks suffer from crowding","volume":"30","author":"Volokitin","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107395_b77","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.1109\/TPAMI.2009.29","article-title":"Rotational invariance based on fourier analysis in polar and spherical coordinates","volume":"31","author":"Wang","year":"2009","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107395_b78","first-page":"245","article-title":"Log-polar mapping applied to pattern representation and recognition","author":"Wilson","year":"1992","journal-title":"Proceedings of the IEEE Computer Vision and Image Processing"},{"key":"10.1016\/j.neunet.2025.107395_b79","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195148220.003.0016","article-title":"How does our visual system achieve shift and size invariance","volume":"322","author":"Wiskott","year":"2006","journal-title":"23 Problems in Systems Neuroscience"},{"key":"10.1016\/j.neunet.2025.107395_b80","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.neunet.2025.107395_b81","series-title":"Scale-invariant convolutional neural networks","author":"Xu","year":"2014"},{"key":"10.1016\/j.neunet.2025.107395_b82","article-title":"Hierarchical modular optimization of convolutional networks achieves representations similar to macaque it and human ventral stream","volume":"26","author":"Yamins","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107395_b83","doi-asserted-by":"crossref","first-page":"8619","DOI":"10.1073\/pnas.1403112111","article-title":"Performance-optimized hierarchical models predict neural responses in higher visual cortex","volume":"111","author":"Yamins","year":"2014","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2025.107395_b84","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.patrec.2022.08.010","article-title":"Rotation invariant gabor convolutional neural network for image classification","volume":"162","author":"Yao","year":"2022","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2025.107395_b85","series-title":"4th international conference on learning representations","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2016"},{"key":"10.1016\/j.neunet.2025.107395_b86","article-title":"Accelerated partially shared dictionary learning with differentiable scale-invariant sparsity for multi-view clustering","author":"Zhao","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107395_b87","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., & Dai, J. (2019). Deformable convnets v2: More deformable, better results. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9308\u20139316).","DOI":"10.1109\/CVPR.2019.00953"},{"key":"10.1016\/j.neunet.2025.107395_b88","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.1109\/TIP.2005.854501","article-title":"Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations","volume":"14","author":"Zokai","year":"2005","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025002746?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025002746?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:07:27Z","timestamp":1762315647000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025002746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":88,"alternative-id":["S0893608025002746"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107395","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enabling scale and rotation invariance in convolutional neural networks with retina like transformation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107395","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107395"}}