{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T05:26:14Z","timestamp":1730957174482,"version":"3.28.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T00:00:00Z","timestamp":1696204800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T00:00:00Z","timestamp":1696204800000},"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":[[2023,10,2]]},"DOI":"10.1109\/iccvw60793.2023.00168","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:31:40Z","timestamp":1703532700000},"page":"1526-1535","source":"Crossref","is-referenced-by-count":0,"title":["RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning"],"prefix":"10.1109","author":[{"given":"Rishabh","family":"Tiwari","sequence":"first","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Arnav","family":"Chavan","sequence":"additional","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Deepak","family":"Gupta","sequence":"additional","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Gowreesh","family":"Mago","sequence":"additional","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Animesh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Akash","family":"Gupta","sequence":"additional","affiliation":[{"name":"NyunAI"}]},{"given":"Suraj","family":"Sharan","sequence":"additional","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Yukun","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group"}]},{"given":"Shanwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ant Group"}]},{"given":"Shihao","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group"}]},{"given":"Youngjun","family":"Kwak","sequence":"additional","affiliation":[{"name":"KakaoBank Corp."}]},{"given":"Seonghun","family":"Jeong","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Yunseung","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Changick","family":"Kim","sequence":"additional","affiliation":[{"name":"KakaoBank Corp."}]},{"given":"Subin","family":"Kim","sequence":"additional","affiliation":[{"name":"KakaoBank Corp."}]},{"given":"Ganzorig","family":"Gankhuyag","sequence":"additional","affiliation":[{"name":"KETI"}]},{"given":"Ho","family":"Jung","sequence":"additional","affiliation":[{"name":"Hanwha Systems"}]},{"given":"Junwhan","family":"Ryu","sequence":"additional","affiliation":[{"name":"Hanwha Systems"}]},{"given":"HaeMoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanwha Systems"}]},{"given":"Byeong H.","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Institute of Industrial Technology"}]},{"given":"Tu","family":"Vo","sequence":"additional","affiliation":[{"name":"KC Machine Learning Lab"}]},{"given":"Sheir","family":"Zaheer","sequence":"additional","affiliation":[{"name":"KC Machine Learning Lab"}]},{"given":"Alexander","family":"Holston","sequence":"additional","affiliation":[{"name":"KC Machine Learning Lab"}]},{"given":"Chan","family":"Park","sequence":"additional","affiliation":[{"name":"KC Machine Learning Lab"}]},{"given":"Dheemant","family":"Dixit","sequence":"additional","affiliation":[{"name":"IIT ISM,Dhanbad"}]},{"given":"Nahush","family":"Lele","sequence":"additional","affiliation":[{"name":"IIT ISM,Dhanbad"}]},{"given":"Kushagra","family":"Bhushan","sequence":"additional","affiliation":[{"name":"IIT ISM,Dhanbad"}]},{"given":"Debjani","family":"Bhowmick","sequence":"additional","affiliation":[{"name":"Transmute AI Lab (Texmin Hub)"}]},{"given":"Devanshu","family":"Arya","sequence":"additional","affiliation":[{"name":"Serket BV"}]},{"given":"Sadaf","family":"Gulshad","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}]},{"given":"Amirhossein","family":"Habibian","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}]},{"given":"Amir","family":"Ghodrati","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}]},{"given":"Babak","family":"Bejnordi","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}]},{"given":"Jai","family":"Gupta","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Zhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta AI Research"}]},{"given":"Jiahui","family":"Yu","sequence":"additional","affiliation":[{"name":"Google Brain"}]},{"given":"Dilip","family":"Prasad","sequence":"additional","affiliation":[{"name":"UiT Tromso"}]},{"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[{"name":"MBUZAI"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/hpca51647.2021.00072"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1085\/2\/022008"},{"journal-title":"Efficient training of language models to fill in the middle","year":"2022","author":"Bavarian","key":"ref3"},{"journal-title":"End to end learning for self-driving cars","year":"2016","author":"Bojarski","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3086892"},{"journal-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref6"},{"journal-title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","year":"2023","author":"Chavan","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00488"},{"journal-title":"Vanillanet: the power of minimalism in deep learning","year":"2023","author":"Chen","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Llm. int8 (): 8-bit matrix multiplication for transformers at scale","year":"2022","author":"Dettmers","key":"ref11"},{"journal-title":"Qlora: Efficient finetuning of quantized llms","year":"2023","author":"Dettmers","key":"ref12"},{"journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2019","author":"Devlin","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"journal-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","year":"2023","author":"Frantar","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00175"},{"article-title":"Ultramnist classification: A benchmark to train cnns for very large images","year":"2022","author":"Gupta","key":"ref17"},{"article-title":"Patch gradient descent: Training neural networks on very large images","year":"2023","author":"Gupta","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00079"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref22"},{"journal-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.189"},{"article-title":"On architectural compression of text-to-image diffusion models","year":"2023","author":"Kim","key":"ref27"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/978-1-4842-6168-2_11","article-title":"Mobilenetv3","author":"Koonce","year":"2021","journal-title":"Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"article-title":"Yolov6: A single-stage object detection framework for industrial applications","year":"2022","author":"Li","key":"ref32"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01608","article-title":"Q-diffusion: Quantizing diffusion models","author":"Li","year":"2023"},{"key":"ref34","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","author":"Lian","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"journal-title":"Oscillation-free quantization for low-bit vision transformers","year":"2023","author":"Liu","key":"ref36"},{"article-title":"Llm-qat: Data-free quantization aware training for large language models","year":"2023","author":"Liu","key":"ref37"},{"article-title":"Rethinking the value of network pruning","volume-title":"International Conference on Learning Representations","author":"Liu","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019563"},{"key":"ref41","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"article-title":"Progressive distillation for fast sampling of diffusion models","year":"2022","author":"Salimans","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref45","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume":"33","author":"Sanh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"A simple and effective pruning approach for large language models","year":"2023","author":"Sun","key":"ref46"},{"key":"ref47","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref48","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research","author":"Tan"},{"journal-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","year":"2020","author":"Tan","key":"ref49"},{"key":"ref50","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00380"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"journal-title":"Benchmarking tpu, gpu, and cpu platforms for deep learning","year":"2019","author":"Wang","key":"ref53"},{"key":"ref54","first-page":"13974","article-title":"Vtc-lfc: Vision transformer compression with low-frequency components","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Resnet strikes back: An improved training procedure in timm","year":"2021","author":"Wightman","key":"ref55"},{"key":"ref56","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research","author":"Xiao"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02170"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","start":{"date-parts":[[2023,10,2]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10350357\/10350360\/10350706.pdf?arnumber=10350706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T20:49:47Z","timestamp":1730926187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10350706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,2]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccvw60793.2023.00168","relation":{},"subject":[],"published":{"date-parts":[[2023,10,2]]}}}