{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T07:30:22Z","timestamp":1771399822931,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"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":[[2025,9,14]]},"DOI":"10.1109\/icipw68931.2025.11386333","type":"proceedings-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:05:43Z","timestamp":1771362343000},"page":"327-332","source":"Crossref","is-referenced-by-count":0,"title":["The Limits of Local Metrics: Investigating the Relationship Between Local Quantization Error and Task Loss in Deep Learning Vision Models"],"prefix":"10.1109","author":[{"given":"Ruixiang","family":"Chai","sequence":"first","affiliation":[{"name":"Northwestern University,Department of Computer Science"}]},{"given":"Peng","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Illinois Springfield,Department of Computer Science"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Black forest labs flux.1-dev model","author":"Labs","year":"2024"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Han"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.08342"},{"key":"ref9","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","author":"Banner","year":"2019","journal-title":"in Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref10","article-title":"Mptq-vit: Mixed-precision post-training quantization for vision transformer","author":"Tai","year":"2024","journal-title":"arXiv preprint arXiv:2401.14895"},{"key":"ref11","article-title":"1.58-bit flux","author":"Yang","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref13","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Frantar"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096817"},{"key":"ref15","article-title":"Improving the speed of neural networks on cpus","volume-title":"Deep Learning and Unsupervised Feature Learning Workshop, Advances in Neural Information Processing Systems (NeurIPS)","author":"Vanhoucke"},{"key":"ref16","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML).","volume":"119","author":"Nagel"},{"key":"ref17","article-title":"Leanquant: Accurate and scalable large language model quantization with loss-error-aware grid","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML).","volume":"202","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06053-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3528042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00286"},{"key":"ref22","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML).","volume":"202","author":"Xiao"},{"key":"ref23","article-title":"Nvidia tensorrt documentation: Quantized types","volume-title":"NVIDIA"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"event":{"name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","location":"Anchorage, AK, USA","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing Workshops (ICIPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11385856\/11385840\/11386333.pdf?arnumber=11386333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T06:56:05Z","timestamp":1771397765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11386333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icipw68931.2025.11386333","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}