{"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/solo-or-ensemble-choosing-a-cnn-architecture","title":"Solo or Ensemble? Choosing a CNN Architecture for Melanoma Classification","arxiv_id":"1904.12724","date":"2019-04-29","proceeding":null,"authors":["Fábio Perez","Sandra Avila","Eduardo Valle"],"abstract":"Convolutional neural networks (CNNs) deliver exceptional results for computer\nvision, including medical image analysis. With the growing number of available\narchitectures, picking one over another is far from obvious. Existing art\nsuggests that, when performing transfer learning, the performance of CNN\narchitectures on ImageNet correlates strongly with their performance on target\ntasks. We evaluate that claim for melanoma classification, over 9 CNNs\narchitectures, in 5 sets of splits created on the ISIC Challenge 2017 dataset,\nand 3 repeated measures, resulting in 135 models. The correlations we found\nwere, to begin with, much smaller than those reported by existing art, and\ndisappeared altogether when we considered only the top-performing networks:\nuncontrolled nuisances (i.e., splits and randomness) overcome any of the\nanalyzed factors. Whenever possible, the best approach for melanoma\nclassification is still to create ensembles of multiple models. We compared two\nchoices for selecting which models to ensemble: picking them at random (among a\npool of high-quality ones) vs. using the validation set to determine which ones\nto pick first. For small ensembles, we found a slight advantage on the second\napproach but found that random choice was also competitive. Although our aim in\nthis paper was not to maximize performance, we easily reached AUCs comparable\nto the first place on the ISIC Challenge 2017.","url_abs":"http://arxiv.org/abs/1904.12724v1","url_pdf":"http://arxiv.org/pdf/1904.12724v1.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":"solo-or-ensemble-choosing-a-cnn-architecture","repo_url":"https://github.com/learningtitans/cvpr-skin-solo-ensemble","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"skin-lesion-classification","task_name":"Skin Lesion Classification"},{"task_slug":"skin-lesion-identification","task_name":"Skin Lesion Identification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.12724","atlas_url":"https://app.syntology.ai/?focus=1904.12724","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":"1904.12724"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.12724\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.12724"},"call":"get_concepts_for_paper(arxiv_id=\"1904.12724\")"}],"by_repo":[{"repo":"learningtitans/cvpr-skin-solo-ensemble","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":"ef9797c3cc962040a8d3c4c5aa601be10f6800b63b055728d87b1722d691ff51","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}