{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:58Z","timestamp":1750309438526,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,19]]},"DOI":"10.1145\/3703790.3703801","type":"proceedings-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T12:30:00Z","timestamp":1744115400000},"page":"90-98","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sensor-Guided Adaptive Machine Learning on Resource-Constrained Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8559-5928","authenticated-orcid":false,"given":"Franz","family":"Papst","sequence":"first","affiliation":[{"name":"Graz University of Technology, Graz, Austria and Complexity Science Hub, Vienna, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8990-0085","authenticated-orcid":false,"given":"Daniel","family":"Kraus","sequence":"additional","affiliation":[{"name":"Pro2Future GmbH, Graz, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3074-3443","authenticated-orcid":false,"given":"Martin","family":"Rechberger","sequence":"additional","affiliation":[{"name":"Graz University of Technology, Graz, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7849-3368","authenticated-orcid":false,"given":"Olga","family":"Saukh","sequence":"additional","affiliation":[{"name":"Graz University of Technology, Graz, Austria and Complexity Science Hub, Vienna, Austria"}]}],"member":"320","published-online":{"date-parts":[[2025,3,31]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"R. Atienza. 2021. Improving Model Generalization by Agreement of Learned Representations from Data Augmentation.","DOI":"10.1109\/WACV51458.2022.00398"},{"key":"e_1_3_3_3_3_2","unstructured":"V. Biscione and J.S. Bowers. 2021. Convolutional Neural Networks Are Not Invariant to Translation but They Can Learn to Be. JMLR 22 229 (2021)."},{"key":"e_1_3_3_3_4_2","unstructured":"N. Cao and O. Saukh. 2023. Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images. arxiv:https:\/\/arXiv.org\/abs\/2311.11029\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.11029"},{"key":"e_1_3_3_3_5_2","unstructured":"A.\u00a0Botev et\u00a0al.. 2022. Regularising for Invariance to Data Augmentation Improves Supervised Learning."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0Sandru et\u00a0al.. 2022. Feature-Level Augmentation to Improve Robustness of Deep Neural Networks to Affine Transformations.","DOI":"10.1007\/978-3-031-25056-9_22"},{"volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","year":"2023","key":"e_1_3_3_3_7_2","unstructured":"C.\u00a0Hou et\u00a0al.. 2023. When to Learn What: Model-Adaptive Data Augmentation Curriculum. In Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_3_3_8_2","series-title":"(EWSN \u201922)","volume-title":"Proceedings of the 2022 International Conference on Embedded Wireless Systems and Networks","year":"2023","unstructured":"C.\u00a0Profentzas et\u00a0al.. 2023. MiniLearn: On-Device Learning for Low-Power IoT Devices. In Proceedings of the 2022 International Conference on Embedded Wireless Systems and Networks(EWSN \u201922)."},{"volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","year":"2019","key":"e_1_3_3_3_9_2","unstructured":"C.\u00a0Sakaridis et\u00a0al.. 2019. Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_3_3_10_2","unstructured":"D.\u00a0Ha et\u00a0al.. 2016. HyperNetworks."},{"key":"e_1_3_3_3_11_2","unstructured":"F.\u00a0Corti et\u00a0al.. 2024. REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints."},{"volume-title":"Advances in Neural Information Processing Systems","year":"2020","key":"e_1_3_3_3_12_2","unstructured":"G.\u00a0Benton et\u00a0al.. 2020. Learning Invariances in Neural Networks from Training Data. In Advances in Neural Information Processing Systems , Vol.\u00a033."},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"G.\u00a0Erion et\u00a0al.. 2021. Improving Performance of Deep Learning Models with Axiomatic Attribution Priors and Expected Gradients. Nature Machine Intelligence 3 7 (July 2021).","DOI":"10.1038\/s42256-021-00343-w"},{"key":"e_1_3_3_3_14_2","unstructured":"G.\u00a0Ilharco et\u00a0al.. 2023. Editing Models with Task Arithmetic."},{"key":"e_1_3_3_3_15_2","unstructured":"H.\u00a0Cai et\u00a0al.. 2022. Network Augmentation for Tiny Deep Learning."},{"key":"e_1_3_3_3_16_2","series-title":"(SenSys \u201923)","volume-title":"Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems","year":"2024","unstructured":"H.\u00a0Chu et\u00a0al.. 2024. nnPerf: Demystifying DNN Runtime Inference Latency on Mobile Platforms. In Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems(SenSys \u201923)."},{"volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","year":"2021","key":"e_1_3_3_3_17_2","unstructured":"H.\u00a0Wu et\u00a0al.. 2021. CvT: Introducing Convolutions to Vision Transformers. In Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision","year":"2017","key":"e_1_3_3_3_18_2","unstructured":"J.\u00a0Dai et\u00a0al.. 2017. Deformable Convolutional Networks. In Proceedings of the IEEE International Conference on Computer Vision."},{"key":"e_1_3_3_3_19_2","unstructured":"J.\u00a0Geiping et\u00a0al.. 2023. How Much Data Are Augmentations Worth? An Investigation into Scaling Laws Invariance and Implicit Regularization."},{"key":"e_1_3_3_3_20_2","unstructured":"J.\u00a0Kaplan et\u00a0al.. 2020. Scaling Laws for Neural Language Models."},{"volume-title":"The 2011 International Joint Conference on Neural Networks","year":"2011","key":"e_1_3_3_3_21_2","unstructured":"J.\u00a0Stallkamp et\u00a0al.. 2011. The German Traffic Sign Recognition Benchmark: A Multi-Class Classification Competition. In The 2011 International Joint Conference on Neural Networks."},{"key":"e_1_3_3_3_22_2","unstructured":"K.\u00a0He et\u00a0al.. 2022. Local Magnification for Data and Feature Augmentation."},{"key":"e_1_3_3_3_23_2","unstructured":"K.\u00a0You et\u00a0al.. 2024. Efficient ConvBN Blocks for Transfer Learning and Beyond."},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"crossref","unstructured":"M.\u00a0G.\u00a0Murshed et\u00a0al.. 2021. Machine Learning at the Network Edge: A Survey. Comput. Surveys 54 8 (Oct. 2021).","DOI":"10.1145\/3469029"},{"volume-title":"Advances in Neural Information Processing Systems","year":"2015","key":"e_1_3_3_3_25_2","unstructured":"M.\u00a0Jaderberg et\u00a0al.. 2015. Spatial Transformer Networks. In Advances in Neural Information Processing Systems , Vol.\u00a028."},{"key":"e_1_3_3_3_26_2","volume-title":"International Conference on Space Optics \u2014 ICSO 2016","volume":"10562","year":"2017","unstructured":"M.\u00a0Maszkiewicz et\u00a0al.. 2017. Fine Guidance Sensor\/near-Infrared Imager and Slitless Spectrograph on James Webb Space Telescope: Pupil Alignment Methodology and Metrology. In International Conference on Space Optics \u2014 ICSO 2016 , Vol.\u00a010562."},{"volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","year":"2021","key":"e_1_3_3_3_27_2","unstructured":"M.\u00a0Poggi et\u00a0al.. 2021. Sensor-Guided Optical Flow. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"crossref","unstructured":"Md.M.H.\u00a0Shuvo et\u00a0al.. 2023. Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review. Proc. IEEE 111 1 (Jan. 2023).","DOI":"10.1109\/JPROC.2022.3226481"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"M.\u00a0Yu et\u00a0al.. 2023. Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study.","DOI":"10.1109\/IJCNN54540.2023.10191736"},{"key":"e_1_3_3_3_30_2","unstructured":"O.\u00a0Saukh et\u00a0al.. 2023. Subspace-Configurable Networks."},{"key":"e_1_3_3_3_31_2","unstructured":"R.\u00a0Entezari et\u00a0al.. 2022. The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks."},{"key":"e_1_3_3_3_32_2","unstructured":"S.\u00a0Mounsaveng et\u00a0al.. 2019. Adversarial Learning of General Transformations for Data Augmentation."},{"key":"e_1_3_3_3_33_2","unstructured":"S.\u00a0Mahan et\u00a0al.. 2021. Rotating Spiders and Reflecting Dogs: A Class Conditional Approach to Learning Data Augmentation Distributions."},{"volume-title":"Proceedings of the 40th International Conference on Machine Learning","year":"2023","key":"e_1_3_3_3_34_2","unstructured":"S.-O.\u00a0Kaba et\u00a0al.. 2023. Equivariance with Learned Canonicalization Functions. In Proceedings of the 40th International Conference on Machine Learning."},{"key":"e_1_3_3_3_35_2","series-title":"(EWSN \u201922)","volume-title":"EWSN","year":"2023","unstructured":"T.\u00a0Goyal et\u00a0al.. 2023. SMiLe: Automated End-to-end Sensing and Machine Learning Co-Design. In EWSN(EWSN \u201922)."},{"volume-title":"Advances in Neural Information Processing Systems","year":"2019","key":"e_1_3_3_3_36_2","unstructured":"T.\u00a0Hahn et\u00a0al.. 2019. Self-Routing Capsule Networks. In Advances in Neural Information Processing Systems , Vol.\u00a032."},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"crossref","unstructured":"W.\u00a0Qi et\u00a0al.. 2021. Multi-Sensor Guided Hand Gesture Recognition for a Teleoperated Robot Using a Recurrent Neural Network. IEEE Robotics and Automation Letters 6 3 (July 2021).","DOI":"10.1109\/LRA.2021.3089999"},{"key":"e_1_3_3_3_38_2","unstructured":"A. Krizhevsky and G. Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. (2009)."},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"A. Mumuni and F. Mumuni. 2021. CNN Architectures for Geometric Transformation-Invariant Feature Representation in Computer Vision: A Review. SN Computer Science 2 5 (June 2021).","DOI":"10.1007\/s42979-021-00735-0"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"A. Mumuni and F. Mumuni. 2022. Data Augmentation: A Comprehensive Survey of Modern Approaches. Array 16 (Dec. 2022).","DOI":"10.1016\/j.array.2022.100258"},{"key":"e_1_3_3_3_41_2","volume-title":"Advances in Neural Information Processing Systems","author":"Neyshabur B.","year":"2020","unstructured":"B. Neyshabur. 2020. Towards Learning Convolutions from Scratch. In Advances in Neural Information Processing Systems , Vol.\u00a033."},{"key":"e_1_3_3_3_42_2","unstructured":"K. O\u2019Shea and R. Nash. 2015. An Introduction to Convolutional Neural Networks."},{"key":"e_1_3_3_3_43_2","unstructured":"J. Schmidt and S. Stober. 2023. Learning Continuous Rotation Canonicalization with Radial Beam Sampling."},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"crossref","unstructured":"C. Shorten and T.M. Khoshgoftaar. 2019. A Survey on Image Data Augmentation for Deep Learning. Journal of Big Data 6 1 (Dec. 2019).","DOI":"10.1186\/s40537-019-0197-0"}],"event":{"name":"IoT 2024: 14th International Conference on the Internet of Things","acronym":"IoT 2024","location":"Oulu Finland"},"container-title":["Proceedings of the 14th International Conference on the Internet of Things"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703790.3703801","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703790.3703801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:42Z","timestamp":1750295382000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703790.3703801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":43,"alternative-id":["10.1145\/3703790.3703801","10.1145\/3703790"],"URL":"https:\/\/doi.org\/10.1145\/3703790.3703801","relation":{},"subject":[],"published":{"date-parts":[[2024,11,19]]},"assertion":[{"value":"2025-03-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}