{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T15:41:49Z","timestamp":1792424509524,"version":"4.5.0"},"reference-count":53,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2020,7,11]],"date-time":"2020-07-11T00:00:00Z","timestamp":1594425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Computer vision is currently one of the most exciting and rapidly evolving fields of science, which affects numerous industries. Research and development breakthroughs, mainly in the field of convolutional neural networks (CNNs), opened the way to unprecedented sensitivity and precision in object detection and recognition tasks. Nevertheless, the findings in recent years on the sensitivity of neural networks to additive noise, light conditions, and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the autonomous robotic industry. In an attempt to bring computer vision algorithms closer to the capabilities of a human operator, the mechanisms of the human visual system was analyzed in this work. Recent studies show that the mechanisms behind the recognition process in the human brain include continuous generation of predictions based on prior knowledge of the world. These predictions enable rapid generation of contextual hypotheses that bias the outcome of the recognition process. This mechanism is especially advantageous in situations of uncertainty, when visual input is ambiguous. In addition, the human visual system continuously updates its knowledge about the world based on the gaps between its prediction and the visual feedback. CNNs are feed forward in nature and lack such top-down contextual attenuation mechanisms. As a result, although they process massive amounts of visual information during their operation, the information is not transformed into knowledge that can be used to generate contextual predictions and improve their performance. In this work, an architecture was designed that aims to integrate the concepts behind the top-down prediction and learning processes of the human visual system with the state-of-the-art bottom-up object recognition models, e.g., deep CNNs. The work focuses on two mechanisms of the human visual system: anticipation-driven perception and reinforcement-driven learning. Imitating these top-down mechanisms, together with the state-of-the-art bottom-up feed-forward algorithms, resulted in an accurate, robust, and continuously improving target recognition model.<\/jats:p>","DOI":"10.3390\/a13070167","type":"journal-article","created":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T04:46:01Z","timestamp":1594701961000},"page":"167","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Biologically Inspired Visual System Architecture for Object Recognition in Autonomous Systems"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4962-1476","authenticated-orcid":false,"given":"Dan","family":"Malowany","sequence":"first","affiliation":[{"name":"The School of Electrical and Computer Engineering, Ben Gurion University of The Negev, P.O. Box 653, Be\u2019er Sheva 84105, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Guterman","sequence":"additional","affiliation":[{"name":"The School of Electrical and Computer Engineering, Ben Gurion University of The Negev, P.O. Box 653, Be\u2019er Sheva 84105, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1584","DOI":"10.1109\/TCSVT.2018.2846695","article-title":"Light Invariant Video Imaging for Improved Performance of Convolution Neural Networks","volume":"29","author":"Kolaman","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., and Clune, J. (2015, January 7\u201312). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1038\/nrn1476","article-title":"Visual objects in context","volume":"5","author":"Bar","year":"2004","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1152\/jn.1992.68.1.70","article-title":"Time course of neural responses discriminating different views of the face and head","volume":"68","author":"Oram","year":"1992","journal-title":"J. Neurophysiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1126\/science.1058249","article-title":"Neuroscience. Seeking categories in the brain","volume":"291","author":"Simon","year":"2001","journal-title":"Science"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/0166-2236(92)90344-8","article-title":"Separate visual pathways for perception and action","volume":"15","author":"Goodale","year":"1992","journal-title":"Trends Neurosci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.tics.2007.05.005","article-title":"The proactive brain: Using analogies and associations to generate predictions","volume":"11","author":"Moshe","year":"2007","journal-title":"Trends Cognit. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1002\/cb.254","article-title":"The proactive brain: Using rudimentary information to make predictive judgments","volume":"330","author":"Bar","year":"2008","journal-title":"J. Consum. Behav."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.visres.2014.12.024","article-title":"The role of visual processing in motor learning and control: Insights from electroencephalography","volume":"110","author":"Krigolson","year":"2015","journal-title":"Vis. Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"12646","DOI":"10.1523\/JNEUROSCI.1872-14.2014","article-title":"Emergent Exploration via Novelty Management","volume":"34","author":"Goren","year":"2014","journal-title":"J. Neurosci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"13402","DOI":"10.1523\/JNEUROSCI.5181-14.2015","article-title":"Simple Learned Weighted Sums of Inferior Temporal Neuronal Firing Rates Accurately Predict Human Core Object Recognition Performance","volume":"35","author":"Majaj","year":"2015","journal-title":"J. Neurosci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, C., Wang, Y., Jiang, T., Fang, F., and Yao, Y. (2011, January 20\u201325). Simulating human saccadic scanpaths on natural images. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2011.5995423"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"066004","DOI":"10.1088\/1741-2560\/9\/6\/066004","article-title":"PAPER Artificial retina: The multichannel processing of the mammalian retina achieved with a neuromorphic asynchronous light acquisition device","volume":"9","author":"Lorach","year":"2012","journal-title":"J. Neural Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., and Torralba, A. (October, January 29). 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_15","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1080\/13506280902834720","article-title":"Modeling Search for People in 900 Scenes: A combined source model of eye guidance","volume":"17","author":"Ehinger","year":"2009","journal-title":"Vis. Cognit."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2109","DOI":"10.1109\/TPAMI.2007.70840","article-title":"Combined Top-Down\/Bottom-Up Segmentation","volume":"30","author":"Eran","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","unstructured":"Vidhya, N., and Laurent, I. (2006, January 17\u201322). An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Spinello, L., Luber, M., and Arras, K.O. (2011, January 9\u201313). Tracking people in 3D using a bottom-up top-down detector. Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, China.","DOI":"10.1109\/ICRA.2011.5980085"},{"key":"ref_19","unstructured":"Lars, K., Chris, B., Marina, A., Akshaya, T., John, F., Patric, J., and Nick, H. (2014, January 14\u201318). Combining Top-down Spatial Reasoning and Bottom-up Object Class Recognition for Scene Understanding. Proceedings of the 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Chicago, IL, USA."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_21","unstructured":"Pierre, S., David, E., Xiang, Z., Michael, M., Rob, F., and LeCun, Y. (2013). OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. arXiv, Available online: https:\/\/arxiv.org\/abs\/1312.6229."},{"key":"ref_22","unstructured":"Karen, S., and Andrew, Z. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv, Available online: https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_24","unstructured":"Ronen, E., and Ohad, S. (2016, January 24). The Power of Depth for Feedforward Neural Networks. Proceedings of the 2016 Journal of Machine Learning Research: Workshop and Conference Proceedings, New York City, NY, USA."},{"key":"ref_25","unstructured":"Telgarsky, M. (2016, January 24). Benefits of depth in neural networks. Proceedings of the 2016 Journal of Machine Learning Research: Workshop and Conference Proceedings, New York City, NY, USA."},{"key":"ref_26","unstructured":"Christian, S., Wojciech, Z., Ilya, S., Joan, B., Dumitru, E., Ian, J.G., and Rob, F. (2014, January 14\u201316). Intriguing properties of neural networks. Proceedings of the International Conference on Learning Representations, Banff, AB, Canada."},{"key":"ref_27","unstructured":"Song, Y., Kim, T., Nowozin, S., Ermon, S., and Kushman, N. (2017). PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples. arXiv, Available online: https:\/\/arxiv.org\/abs\/1710.10766."},{"key":"ref_28","unstructured":"Moosavi, D., Seyed, M., Fawzi, A., and Frossard, P. (2016, January 30). DeepFool: A simple and accurate method to fool deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_29","first-page":"70","article-title":"Deep Reinforcement Learning framework for Autonomous Driving","volume":"19","author":"Sallab","year":"2017","journal-title":"Electro. Imag."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"ref_31","first-page":"1140","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play","volume":"362","author":"Silver","year":"2018","journal-title":"Am. Assoc. Adv. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/s42256-019-0025-4","article-title":"Reinforcement learning in artificial and biological systems","volume":"1","author":"Neftci","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0010-0285(92)90007-O","article-title":"The reviewing of object files: Object- specific integration of information","volume":"24","author":"Daniel","year":"1992","journal-title":"Cognit. Psychol."},{"key":"ref_34","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the Advances in Neural Information Processing Systems 27 (NIPS 2015), Montreal, QC, Canada."},{"key":"ref_35","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., and Oliva, A. (2014, January 8\u201313). Learning deep features for scene recognition using places database. Proceedings of the Advances in Neural Information Processing Systems 27 (NIPS 2014), Montreal, QC, Canada."},{"key":"ref_36","unstructured":"Dale, P., Roberto, C., Scott, A.H., Kevin, S.L., Michael, L.P., and Marty, G.W. (2013). Cognitive Neuroscience, Sinauer Associates. [2nd ed.]."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"KaewtrakulpongPakorn, P., and Bowden, K.B. (2001). An Improved Adaptive Background Mixture Model for Real- Time Tracking with Shadow Detection, Video-Based Surveillance Systems, Springer.","DOI":"10.1007\/978-1-4615-0913-4_11"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1088\/0954-898X_14_3_302","article-title":"Statistics of natural image categories","volume":"14","author":"Antonio","year":"2003","journal-title":"Network"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","article-title":"Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope","volume":"42","author":"Aude","year":"2001","journal-title":"Int. J. Comput. Vis."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1037\/0096-3445.108.3.316","article-title":"Framing pictures: The role of knowledge in automatized encoding and memory for gist","volume":"108","author":"Friedman","year":"1979","journal-title":"J. Exp. Psychol. Gen."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"324","DOI":"10.3758\/BF03206495","article-title":"The persistence of object file representations","volume":"67","author":"Nicholaus","year":"2005","journal-title":"Percept. Psychophys."},{"key":"ref_42","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_43","unstructured":"Gu, S., Lillicrap, T., Sutskever, I., and Levine, S. (2016, January 20\u201322). Continuous deep Q-learning with model-based acceleration. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1177\/0278364917710318","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"37","author":"Levine","year":"2018","journal-title":"Int. J. Robot. Res."},{"key":"ref_46","unstructured":"James, K., Razvan, P., Neil, R., Joel, V., Guillaume, D., Andrei, A.R., Kieran, M., John, Q., Tiago, R., and Agnieszka, G.-B. (2020, July 11). Overcoming Catastrophic Forgetting in Neural Networks. Available online: https:\/\/www.pnas.org\/content\/114\/13\/3521."},{"key":"ref_47","unstructured":"Huang, F.J., and LeCun, Y. (2006, January 17\u201322). Large-scale learning with svm and convolutional for generic object categorization. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), New York, NY, USA."},{"key":"ref_48","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume":"15","author":"Adam","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_49","unstructured":"Yichuan, T. (2013). Deep learning using linear support vector machines. arXiv, Available online: https:\/\/arxiv.org\/pdf\/1306.0239."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., and Darrell, T. (2015, January 7\u201312). Long-Term Recurrent Convolutional Networks for Visual Recognition and Description. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref_52","unstructured":"Alfred, L.Y. (1967). Eye Movements and Vision, Springer."},{"key":"ref_53","first-page":"1","article-title":"Defending Yarbus: Eye movements reveal observers\u2019 task","volume":"14","author":"Ali","year":"2014","journal-title":"J. Vis."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/13\/7\/167\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:50:21Z","timestamp":1760176221000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/13\/7\/167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,11]]},"references-count":53,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2020,7]]}},"alternative-id":["a13070167"],"URL":"https:\/\/doi.org\/10.3390\/a13070167","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,11]]}}}