{"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/masked-image-residual-learning-for-scaling-1","title":"Masked Image Residual Learning for Scaling Deeper Vision Transformers","arxiv_id":"2309.14136","date":"2023-09-25","proceeding":"NeurIPS 2023 11","authors":["Guoxi Huang","Hongtao Fu","Adrian G. Bors"],"abstract":"Deeper Vision Transformers (ViTs) are more challenging to train. We expose a degradation problem in deeper layers of ViT when using masked image modeling (MIM) for pre-training. To ease the training of deeper ViTs, we introduce a self-supervised learning framework called Masked Image Residual Learning (MIRL), which significantly alleviates the degradation problem, making scaling ViT along depth a promising direction for performance upgrade. We reformulate the pre-training objective for deeper layers of ViT as learning to recover the residual of the masked image. We provide extensive empirical evidence showing that deeper ViTs can be effectively optimized using MIRL and easily gain accuracy from increased depth. With the same level of computational complexity as ViT-Base and ViT-Large, we instantiate 4.5$\\times$ and 2$\\times$ deeper ViTs, dubbed ViT-S-54 and ViT-B-48. The deeper ViT-S-54, costing 3$\\times$ less than ViT-Large, achieves performance on par with ViT-Large. ViT-B-48 achieves 86.2% top-1 accuracy on ImageNet. On one hand, deeper ViTs pre-trained with MIRL exhibit excellent generalization capabilities on downstream tasks, such as object detection and semantic segmentation. On the other hand, MIRL demonstrates high pre-training efficiency. With less pre-training time, MIRL yields competitive performance compared to other approaches.","url_abs":"https://arxiv.org/abs/2309.14136v3","url_pdf":"https://arxiv.org/pdf/2309.14136v3.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":"masked-image-residual-learning-for-scaling-1","repo_url":"https://github.com/russellllaputa/MIRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MIRL (ViT-B-48)","rank_in_archive_order":170,"of":1060,"metrics":{"GFLOPs":"67.0","Number of params":"341M","Top 1 Accuracy":"86.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MIRL(ViT-S-54)","rank_in_archive_order":290,"of":1060,"metrics":{"GFLOPs":"18.8","Number of params":"96M","Top 1 Accuracy":"84.8%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on-1","task":"Self-Supervised Image Classification","dataset":"ImageNet (finetuned)","model":"MIRL (ViT-B-48)","rank_in_archive_order":16,"of":65,"metrics":{"Number of Params":"341M","Top 1 Accuracy":"86.2%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on-1","task":"Self-Supervised Image Classification","dataset":"ImageNet (finetuned)","model":"MIRL (ViT-S-54)","rank_in_archive_order":27,"of":65,"metrics":{"Number of Params":"96M","Top 1 Accuracy":"84.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.14136","atlas_url":"https://app.syntology.ai/?focus=2309.14136","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":"2309.14136"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.14136\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.14136"},"call":"get_concepts_for_paper(arxiv_id=\"2309.14136\")"}],"by_repo":[{"repo":"russellllaputa/MIRL","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":"8fc24f0df6e83d74d325f8f3fa5cc075e3da55ae7f67db9ba42043798ca437f7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}