{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:35:13Z","timestamp":1730237713288,"version":"3.28.0"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.01571","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"17084-17095","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Computation Sharing for Multi-Task Visual Scene Understanding"],"prefix":"10.1109","author":[{"given":"Sara","family":"Shoouri","sequence":"first","affiliation":[{"name":"University of Michigan"}]},{"given":"Mingyu","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Zichen","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Hun-Seok","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Michigan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01172"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Advances in neural information processing systems","volume":"33","author":"Caron"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref9","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904360"},{"key":"ref11","first-page":"2039","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","volume-title":"Advances in neural information processing systems","volume":"33","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref13"},{"article-title":"Few-shot learning via learning the representation, provably","volume-title":"International Conference on Learning Representations","author":"Du","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014067"},{"key":"ref17","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Advances in neural information processing systems","volume":"34","author":"Fifty"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.378"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"article-title":"Parameter-efficient fine-tuning for vision transformers","year":"2022","author":"He","key":"ref24"},{"article-title":"Gaussian error linear units (gelus)","year":"2016","author":"Hendrycks","key":"ref25"},{"key":"ref26","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International Conference on Machine Learning","author":"Houlsby"},{"article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.509"},{"key":"ref29","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Advances in neural information processing systems","volume":"34","author":"Mahabadi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref32","first-page":"1723","article-title":"Learning task grouping and overlap in multi-task learning","volume-title":"Proceedings of the 29th International Coference on International Conference on Machine Learning","author":"Kumar"},{"article-title":"Fine-tuning can distort pre-trained features and underperform out-of-distribution","volume-title":"International Conference on Learning Representations","author":"Kumar","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01931-6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"article-title":"Decoupled weight decay regularization","volume-title":"iclr, 2019","author":"Loshchilov","key":"ref39"},{"article-title":"Learning sparse neural networks through l_0 regularization","volume-title":"International Conference on Learning Representations","author":"Louizos","key":"ref40"},{"article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"International Conference on Learning Representations","author":"Maddison","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564969"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00858"},{"key":"ref46","first-page":"4055","article-title":"Image transformer","volume-title":"International conference on machine learning","author":"Parmar"},{"article-title":"Carbon emissions and large neural network training","year":"2021","author":"Patterson","key":"ref47"},{"key":"ref48","article-title":"Stand-alone self-attention in vision models","volume-title":"Advances in neural information processing systems","volume":"32","author":"Ramachandran"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref50","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Advances in neural information processing systems","volume":"33","author":"Sanh"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00194"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref53","first-page":"5986","article-title":"Bert and pals: Projected attention layers for efficient adaptation in multi-task learning","volume-title":"International Conference on Machine Learning","author":"Stickland"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.541"},{"key":"ref57","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron"},{"key":"ref58","first-page":"7852","article-title":"On the theory of transfer learning: The importance of task diversity","volume-title":"Advances in neural information processing systems","volume":"33","author":"Tripuraneni"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.496"},{"article-title":"Understanding and improving information transfer in multi-task learning","volume-title":"International Conference on Learning Representations","author":"Wu","key":"ref64"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2626959"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519448"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01121"},{"article-title":"Adadelta: an adaptive learning rate method","year":"2012","author":"Zeiler","key":"ref71"},{"article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","year":"2019","author":"Zhai","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475501"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.174"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00457"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations","author":"Zhu","key":"ref78"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2023,10,1]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378492.pdf?arnumber=10378492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:30:22Z","timestamp":1705541422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.01571","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}