{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:36:18Z","timestamp":1770845778734,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343501","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"3855-3860","source":"Crossref","is-referenced-by-count":0,"title":["Tuning Distillation to Generate Edge-friendly All-rounder Models"],"prefix":"10.1109","author":[{"given":"Swarnava","family":"Dey","sequence":"first","affiliation":[{"name":"Tata Consultancy Services Limited,TCS Research,Kolkata,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arijit","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services Limited,TCS Research,Kolkata,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arpan","family":"Pal","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services Limited,TCS Research,Kolkata,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref2","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops59983.2024.10502805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3597061.3597259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops56833.2023.10150280"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3510027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00182"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops56833.2023.10150311"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops59983.2024.10503237"},{"key":"ref12","article-title":"Semi-supervised on-device neural network adaptation for remote and portable laser-induced breakdown spectroscopy","author":"Bhardwaj","year":"2021"},{"key":"ref13","article-title":"What do compressed deep neural networks forget?","author":"Hooker","year":"2021"},{"key":"ref14","article-title":"Lost in pruning: The effects of pruning neural networks beyond test accuracy","author":"Liebenwein","year":"2021"},{"key":"ref15","article-title":"Seed: Self-supervised distillation for visual representation","author":"Fang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3662006.3662061"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.01619","article-title":"On robustness and transferability of convolutional neural networks","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Djolonga"},{"key":"ref18","article-title":"Assaying out-of-distribution generalization in transfer learning","volume-title":"Advances in Neural Information Processing Systems","author":"Wenzel","year":"2022"},{"key":"ref19","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Hendrycks"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref21","article-title":"The evolution of out-of-distribution robustness throughout fine-tuning","volume-title":"Transactions on Machine Learning Research","author":"Andreassen","year":"2022"},{"key":"ref22","article-title":"Resnet-9","year":"2024"},{"key":"ref23","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"University of Toronto, Toronto, Ontario, Tech. Rep. 0"},{"key":"ref24","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"ICLR"},{"key":"ref25","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2019"},{"key":"ref26","article-title":"Robust binary models by pruning randomly-initialized networks","author":"Liu","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref29","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref30","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref31","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"ref32","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01549"},{"key":"ref34","article-title":"Contrastive representation distillation","author":"Tian","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"ref36","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020"},{"key":"ref37","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2","author":"Yosinski"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref39","article-title":"pytorch-cifar","year":"2021"},{"key":"ref40","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2015"},{"key":"ref41","first-page":"10 929","article-title":"RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Garrido"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref43","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Li","year":"2018"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343501.pdf?arnumber=11343501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:51:38Z","timestamp":1770843098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343501","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}