{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:45:12Z","timestamp":1774928712422,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>Neural architecture search (NAS) and network pruning are widely studied efficient AI techniques, but not yet perfect.\n\nNAS performs exhaustive candidate architecture search, incurring tremendous search cost.\n\nThough (structured) pruning can simply shrink model dimension, it remains unclear how to decide the per-layer sparsity automatically and optimally.\n\nIn this work, we revisit the problem of layer-width optimization and propose Pruning-as-Search (PaS), an end-to-end channel pruning method to  search out desired sub-network automatically and efficiently.\n\nSpecifically, we add a depth-wise binary convolution to learn pruning policies directly through gradient descent.\n\nBy combining the structural reparameterization and PaS, we successfully searched out a new family of VGG-like and lightweight networks, which enable the flexibility of arbitrary width with respect to each layer instead of each stage.\n\nExperimental results show that our proposed architecture outperforms prior arts by around 1.0% top-1 accuracy under similar inference speed on ImageNet-1000 classification task.\n\nFurthermore, we demonstrate the effectiveness of our width search on complex tasks including instance segmentation and image translation.\n\nCode and models are released.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/449","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"3236-3242","source":"Crossref","is-referenced-by-count":32,"title":["Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization"],"prefix":"10.24963","author":[{"given":"Yanyu","family":"Li","sequence":"first","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Intel Corp."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","theme":"Artificial Intelligence","location":"Vienna, Austria","acronym":"IJCAI-2022","number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2022,7,23]]},"end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:09:47Z","timestamp":1658142587000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/449"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/449","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}