{"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/rescaling-large-datasets-based-on-validation","title":"Rescaling Large Datasets Based on Validation Outcomes of a Pre-trained Network","arxiv_id":null,"date":"2024-07-01","proceeding":"Pattern Recognition Letters 2024 7","authors":["Thanh Tuan NGUYEN","Thanh Phuong Nguyen"],"abstract":"In fact, several categories in a large dataset are not difficult for recent advanced deep\r\nneural networks to recognize. Eliminating them for a challenging smaller subset will\r\nassist the early network proposals in taking a quick trial of verification. To this end, we\r\npropose an efficient rescaling method based on the validation outcomes of a pre-trained\r\nmodel. Firstly, we will take out the sensitive images of the lowest-accuracy classes\r\nof the validation outcomes. Each of such images is then considered to identify which\r\nlabel it was confused with. Gathering the lowest-accuracy classes along with the most\r\nconfused ones can produce a smaller subset with a higher challenge for quick validation\r\nof an early network draft. Finally, a rescaling application is introduced to rescale two\r\npopular large datasets (ImageNet and Places365) for different tiny subsets (i.e., ReINΩ\r\nand RePLΩ respectively). Experiments for image classification have proved that neural\r\nnetworks obtaining good performance on the original datasets also achieve good results\r\non their rescaled subsets. For instance, MobileNetV1 and MobileNetV2 with 70.6%\r\nand 72% on ImageNet respectively obtained 46.53% and 47.47% on its small subset\r\nReIN30, which only contains about 39000 images. It can be observed that the better\r\nperformance of MobileNetV2 on ImageNet correspondingly leads to the better rate on\r\nits rescaled subset. Appropriately, utilizing these rescaled sets would help researchers\r\nsave time and computational costs in the way of designing deep neural architectures.","url_abs":"https://github.com/nttbdrk25/ImageNetPlaces365","url_pdf":"https://github.com/nttbdrk25/ImageNetPlaces365","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":"rescaling-large-datasets-based-on-validation","repo_url":"https://github.com/nttbdrk25/ImageNetPlaces365","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"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":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"rein-and-repl","name":"ReINs and RePLs: Challenging, small datasets for quick validations of designing deep neural networks for image classification","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"nttbdrk25/ImageNetPlaces365","kind":"listed","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":"0f27dd8a1f18d9b65fc810873be759df0e7b13e75e8645629ef759a06282161c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}