{"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/meal-v2-boosting-vanilla-resnet-50-to-80-top","title":"MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks","arxiv_id":"2009.08453","date":"2020-09-17","proceeding":null,"authors":["Zhiqiang Shen","Marios Savvides"],"abstract":"We introduce a simple yet effective distillation framework that is able to boost the vanilla ResNet-50 to 80%+ Top-1 accuracy on ImageNet without tricks. We construct such a framework through analyzing the problems in the existing classification system and simplify the base method ensemble knowledge distillation via discriminators by: (1) adopting the similarity loss and discriminator only on the final outputs and (2) using the average of softmax probabilities from all teacher ensembles as the stronger supervision. Intriguingly, three novel perspectives are presented for distillation: (1) weight decay can be weakened or even completely removed since the soft label also has a regularization effect; (2) using a good initialization for students is critical; and (3) one-hot/hard label is not necessary in the distillation process if the weights are well initialized. We show that such a straight-forward framework can achieve state-of-the-art results without involving any commonly-used techniques, such as architecture modification; outside training data beyond ImageNet; autoaug/randaug; cosine learning rate; mixup/cutmix training; label smoothing; etc. Our method obtains 80.67% top-1 accuracy on ImageNet using a single crop-size of 224x224 with vanilla ResNet-50, outperforming the previous state-of-the-arts by a significant margin under the same network structure. Our result can be regarded as a strong baseline using knowledge distillation, and to our best knowledge, this is also the first method that is able to boost vanilla ResNet-50 to surpass 80% on ImageNet without architecture modification or additional training data. On smaller ResNet-18, our distillation framework consistently improves from 69.76% to 73.19%, which shows tremendous practical values in real-world applications. Our code and models are available at: https://github.com/szq0214/MEAL-V2.","url_abs":"https://arxiv.org/abs/2009.08453v2","url_pdf":"https://arxiv.org/pdf/2009.08453v2.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":"meal-v2-boosting-vanilla-resnet-50-to-80-top","repo_url":"https://github.com/szq0214/MEAL-V2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MEAL V2 (ResNet-50) (380 res)","rank_in_archive_order":612,"of":1060,"metrics":{"Number of params":"25.6M","Top 1 Accuracy":"81.72%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MEAL V2 (ResNet-50) (224 res)","rank_in_archive_order":687,"of":1060,"metrics":{"Top 1 Accuracy":"80.67%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-18 (MEAL V2)","rank_in_archive_order":989,"of":1060,"metrics":{"Top 1 Accuracy":"73.19%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-omnibenchmark","task":"Image Classification","dataset":"OmniBenchmark","model":"MEAL-V2","rank_in_archive_order":11,"of":22,"metrics":{"Average Top-1 Accuracy":"36.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.08453","atlas_url":"https://app.syntology.ai/?focus=2009.08453","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":"2009.08453"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2009.08453\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2009.08453"},"call":"get_concepts_for_paper(arxiv_id=\"2009.08453\")"}],"by_repo":[{"repo":"szq0214/MEAL-V2","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":"18aa965095ae03614958940151deb026c06f5c8dc742b5adbc7654ce8906d3f7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}