{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T17:48:54Z","timestamp":1783014534245,"version":"3.54.6"},"reference-count":39,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Postdoctoral Programme of Smart Tower Co., Ltd."},{"name":"Phase I Research on Large-Scale Models for the Spatial Governance Industry"},{"name":"Phase II Research on Large-Scale Models for the Spatial Governance Industry"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Biologically inspired retinal preprocessing improves visual perception by efficiently encoding and reducing entropy in images. In this study, we introduce a new saliency prediction framework that combines a retinal model with deep neural networks (DNNs) using information theory ideas. By mimicking the human retina, our method creates clearer saliency maps with lower entropy and supports efficient computation with DNNs by optimizing information flow and reducing redundancy. We treat saliency prediction as an information maximization problem, where important regions have high information and low local entropy. Tests on several benchmark datasets show that adding the retinal model boosts the performance of various bottom-up saliency prediction methods by better managing information and reducing uncertainty. We use metrics like mutual information and entropy to measure improvements in accuracy and efficiency. Our framework outperforms state-of-the-art models, producing saliency maps that closely match where people actually look. By combining neurobiological insights with information theory\u2014using measures like Kullback\u2013Leibler divergence and information gain\u2014our method not only improves prediction accuracy but also offers a clear, quantitative understanding of saliency. This approach shows promise for future research that brings together neuroscience, entropy, and deep learning to enhance visual saliency prediction.<\/jats:p>","DOI":"10.3390\/e27040436","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T23:16:46Z","timestamp":1744931806000},"page":"436","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Retina-Inspired Models Enhance Visual Saliency Prediction"],"prefix":"10.3390","volume":"27","author":[{"given":"Gang","family":"Shen","sequence":"first","affiliation":[{"name":"Smart Tower Co., Ltd., Beijing 100089, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Ma","sequence":"additional","affiliation":[{"name":"Smart Tower Co., Ltd., Beijing 100089, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Zhai","sequence":"additional","affiliation":[{"name":"State Unclear Electric Power Planning Design & Research Institute Co., Ltd., Beijing 100095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefei","family":"Lv","sequence":"additional","affiliation":[{"name":"Smart Tower Co., Ltd., Beijing 100089, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing 100191, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing 100191, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"key":"ref_1","unstructured":"Wohrer, A. (2008). The Vertebrate Retina: A Functional Review. [Ph.D. Thesis, INRIA]."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s11263-009-0215-3","article-title":"Modelling spatio-temporal saliency to predict gaze direction for short videos","volume":"82","author":"Marat","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liu, P., Xu, T., Shi, G., Xu, J., Chen, H., and Li, J. (2024). Spectrum-oriented Point-supervised Saliency Detector for Hyperspectral Images. arXiv.","DOI":"10.1109\/TIM.2025.3527488"},{"key":"ref_4","unstructured":"Moskalenko, A., Bryncev, A., Vatolin, D., Timofte, R., Zhan, G., Yang, L., Tang, Y., Liao, Y., Lin, J., and Huang, B. (2024, January 29). AIM 2024 Challenge on Video Saliency Prediction: Methods and Results. Proceedings of the 18th European Conference on Computer Vision ECCV 2024, Advances in Image Manipulation Workshop, Milan, Italy."},{"key":"ref_5","unstructured":"Zhong, H., Huang, M., Dai, W.P., Wang, H., Roe, A.W., and Yu, Y. (2024, January 9\u201315). Visual Pinwheel Center Act as Geometric Saliency Detector. Proceedings of the the Thirty-Eighth Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_6","unstructured":"Bellitto, G., Salanitri, F.P., Pennisi, M., Boschini, M., Bonicelli, L., Porrello, A., Calderara, S., Palazzo, S., and Spampinato, C. (2024). Saliency-driven Experience Replay for Continual Learning. Advances in Neural Information Processing Systems 38 (NeurIPS 2024), Proceedings of the Thirty-Eighth Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 9\u201315 December 2024, NeurIPS."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5173","DOI":"10.1007\/s11263-024-02051-5","article-title":"ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection","volume":"132","author":"Lin","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1109\/TIP.2023.3234702","article-title":"CAVER: Cross-modal view-mixed transformer for bi-modal salient object detection","volume":"32","author":"Pang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9026","DOI":"10.1109\/TPAMI.2021.3122139","article-title":"Learning selective mutual attention and contrast for RGB-D saliency detection","volume":"44","author":"Liu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, G., and Chen, Z. (2018). Saliency Detection by Superpixel-Based Sparse Representation. Advances in Multimedia Information Processing\u2013PCM 2017, Proceedings of the 18th Pacific-Rim Conference on Multimedia, Harbin, China, 28\u201329 September 2017, Springer.","DOI":"10.1007\/978-3-319-77383-4_44"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0893-6080(88)90024-X","article-title":"A silicon model of early visual processing","volume":"1","author":"Mead","year":"1988","journal-title":"Neural Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s10827-008-0108-4","article-title":"Virtual retina: A biological retina model and simulator, with contrast gain control","volume":"26","author":"Wohrer","year":"2009","journal-title":"J. Comput. Neurosci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1016\/j.cviu.2010.01.011","article-title":"Using human visual system modeling for bio-inspired low level image processing","volume":"114","author":"Benoit","year":"2010","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., and Perona, P. (2006). Graph-based visual saliency. Adv. Neural Inf. Process. Syst., 19.","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cichy, R.M., Khosla, A., Pantazis, D., Torralba, A., and Oliva, A. (2016). Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence. Sci. Rep., 6.","DOI":"10.1038\/srep27755"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A model of saliency-based visual attention for rapid scene analysis","volume":"20","author":"Itti","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Sclaroff, S. (2013, January 1\u20138). Saliency detection: A boolean map approach. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia.","DOI":"10.1109\/ICCV.2013.26"},{"key":"ref_18","unstructured":"Chen, G., Peng, P., Huang, Y., Geng, M., and Tian, Y. (2024, January 20\u201327). Adaptive Discovering and Merging for Incremental Novel Class Discovery. Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), Vancouver, BC, Canada."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Vig, E., Dorr, M., and Cox, D. (2014, January 23\u201328). Large-scale optimization of hierarchical features for saliency prediction in natural images. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref_20","unstructured":"K\u00fcmmerer, M., Theis, L., and Bethge, M. (2015, January 7\u20139). Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., and Zhao, Q. (2015, January 7\u201313). Salicon: Reducing the semantic gap in saliency prediction by adapting deep neural networks. Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"H\u00e9rault, J., and Durette, B. (2007). Modeling visual perception for image processing. Computational and Ambient Intelligence, Proceedings of the 9th International Work-Conference on Artificial Neural Networks, IWANN 2007, San Sebasti\u00e1n, Spain, 20\u201322 June 2007, Springer.","DOI":"10.1007\/978-3-540-73007-1_80"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1088\/0954-898X_7_2_012","article-title":"Sensory coding in the vertebrate retina: Towards an adaptive control of visual sensitivity","volume":"7","author":"Beaudot","year":"1996","journal-title":"Netw. Comput. Neural Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1038\/386069a0","article-title":"Adaptation of retinal processing to image contrast and spatial scale","volume":"386","author":"Smirnakis","year":"1997","journal-title":"Nature"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1038\/nn1228","article-title":"Multiple neural spike train data analysis: State-of-the-art and future challenges","volume":"7","author":"Brown","year":"2004","journal-title":"Nat. Neurosci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 26\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Han, W., Chang, S., Liu, D., Yu, M., Witbrock, M., and Huang, T.S. (2018, January 18\u201323). Image super-resolution via dual-state recurrent networks. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00178"},{"key":"ref_29","unstructured":"Simonyan, K. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5142","DOI":"10.1109\/TIP.2018.2851672","article-title":"Predicting human eye fixations via an lstm-based saliency attentive model","volume":"27","author":"Cornia","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Jiang, M., Huang, S., Duan, J., and Zhao, Q. (2015, January 7\u201312). Salicon: Saliency in context. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref_32","unstructured":"Bruce, N., and Tsotsos, J. (2005). Saliency based on information maximization. Adv. Neural Inf. Process. Syst., 18."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., and Torralba, A. (2010, January 6). Learning to predict where humans look. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan.","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Murray, N., Vanrell, M., Otazu, X., and Parraga, C.A. (2011, January 20\u201325). Saliency estimation using a non-parametric low-level vision model. Proceedings of the CVPR, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"ref_35","unstructured":"Hou, X., and Zhang, L. (2008). Dynamic visual attention: Searching for coding length increments. Adv. Neural Inf. Process. Syst., 21."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1167\/8.7.32","article-title":"SUN: A Bayesian framework for saliency using natural statistics","volume":"8","author":"Zhang","year":"2008","journal-title":"J. Vis."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., and Susstrunk, S. (2009, January 20\u201325). Frequency-tuned salient region detection. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPRW.2009.5206596"},{"key":"ref_38","unstructured":"Tavakoli, H.R., and Laaksonen, J. (2017). Bottom-up fixation prediction using unsupervised hierarchical models. Computer Vision, Proceedings of the ACCV 2016 Workshops: ACCV 2016 International Workshops, Taipei, Taiwan, 20\u201324 November 2016, Springer."},{"key":"ref_39","unstructured":"Radarapu, R., Velusamy, S., Hegde, A., and Kothari, N. (2025, January 13). FixPNet: Attention Guided Fixation Map Prediction with Explicit Image Priors. Available online: https:\/\/computer-vision-in-the-wild.github.io\/cvpr-2023\/static\/cvpr2023\/accepted_papers\/13\/CameraReady\/CVinW__23.pdf."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/4\/436\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:16:54Z","timestamp":1760030214000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/4\/436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,18]]},"references-count":39,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["e27040436"],"URL":"https:\/\/doi.org\/10.3390\/e27040436","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,18]]}}}