{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/scarletnas-bridging-the-gap-between","title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","arxiv_id":"1908.06022","date":"2019-08-16","proceeding":null,"authors":["Xiangxiang Chu","Bo Zhang","Qingyuan Li","Ruijun Xu","Xudong Li"],"abstract":"To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. It seems handy to include an additional skip connection in the search space to make depths variable. However, it creates a large range of perturbation during supernet training and it has difficulty giving a confident ranking for subnetworks. In this paper, we discover that skip connections bring about significant feature inconsistency compared with other operations, which potentially degrades the supernet performance. Based on this observation, we tackle the problem by imposing an equivariant learnable stabilizer to homogenize such disparities. Experiments show that our proposed stabilizer helps to improve the supernet's convergence as well as ranking performance. With an evolutionary search backend that incorporates the stabilized supernet as an evaluator, we derive a family of state-of-the-art architectures, the SCARLET series of several depths, especially SCARLET-A obtains 76.9% top-1 accuracy on ImageNet. Code is available at https://github.com/xiaomi-automl/ScarletNAS.","url_abs":"https://arxiv.org/abs/1908.06022v6","url_pdf":"https://arxiv.org/pdf/1908.06022v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scarletnas-bridging-the-gap-between","repo_url":"https://github.com/xiaomi-automl/SCARLET-NAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"cutout","method_name":"Cutout"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"scarlet","method_name":"SCARLET"},{"method_slug":"scarlet-nas","method_name":"SCARLET-NAS"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"scarlet-nas","name":"SCARLET-NAS","full_name":"SCARLET-NAS"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SCARLET-A4","rank_in_archive_order":551,"of":1060,"metrics":{"GFLOPs":"8.4","Hardware Burden":"12G","Number of params":"27.8M","Operations per network pass":"0.42G","Top 1 Accuracy":"82.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SCARLET-A","rank_in_archive_order":895,"of":1060,"metrics":{"GFLOPs":"0.730","Number of params":"6.7M","Top 1 Accuracy":"76.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SCARLET-B","rank_in_archive_order":919,"of":1060,"metrics":{"GFLOPs":"0.658","Number of params":"6.5M","Top 1 Accuracy":"76.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SCARLET-C","rank_in_archive_order":945,"of":1060,"metrics":{"GFLOPs":"0.560","Number of params":"6M","Top 1 Accuracy":"75.6%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"SCARLET-A","rank_in_archive_order":76,"of":135,"metrics":{"Accuracy":"76.9","MACs":"365M","Params":"6.7M","Top-1 Error Rate":"23.1"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"SCARLET-B","rank_in_archive_order":86,"of":135,"metrics":{"Accuracy":"76.3","MACs":"329M","Params":"6.5M","Top-1 Error Rate":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"SCARLET-C","rank_in_archive_order":103,"of":135,"metrics":{"Accuracy":"75.6","MACs":"280M","Params":"6.0M","Top-1 Error Rate":"24.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.06022","atlas_url":"https://app.syntology.ai/?focus=1908.06022","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1908.06022"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1908.06022\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1908.06022"},"call":"get_concepts_for_paper(arxiv_id=\"1908.06022\")"}],"by_repo":[{"repo":"xiaomi-automl/SCARLET-NAS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a4ef30e5a1bb523d2d95c8029c6bfbdd7d2ca3e454e838c9669e40c8383dd723","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}