{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/learning-from-small-samples-transformation","title":"Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales","arxiv_id":"2109.12784","date":"2021-09-27","proceeding":null,"authors":["Tao Liu","P. R. Kumar","Ruida Zhou","Xi Liu"],"abstract":"Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful. Particularly important is the ability to incorporate domain knowledge of invariances, e.g., translational invariance of images. Kernels based on the \\textit{maximum} similarity over a group of transformations are not generally positive definite. Perhaps it is for this reason that they have not been studied theoretically. We address this lacuna and show that positive definiteness indeed holds \\textit{with high probability} for kernels based on the maximum similarity in the small training sample set regime of interest, and that they do yield the best results in that regime. We also show how additional properties such as their ability to incorporate local features at multiple spatial scales, e.g., as done in CNNs through max pooling, and to provide the benefits of composition through the architecture of multiple layers, can also be embedded into SVMs. We verify through experiments on widely available image sets that the resulting SVMs do provide superior accuracy in comparison to well-established deep neural network benchmarks for small sample sizes.","url_abs":"https://arxiv.org/abs/2109.12784v6","url_pdf":"https://arxiv.org/pdf/2109.12784v6.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":"learning-from-small-samples-transformation","repo_url":"https://github.com/tliu1997/ti-svm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.12784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12784"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/tliu1997/TI-SVM","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tliu1997/ti-svm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7e7b5a912d0c33d0","entry":"rotation_preprocess","repo":"tliu1997/TI-SVM","repo_kind":"official","path":"TMNIST/ImageUtils.py","file_url":"https://github.com/tliu1997/TI-SVM/blob/HEAD/TMNIST/ImageUtils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e7b5a912d0c33d0"}},{"code_sha256_prefix":"4097b9b9d715cd45","entry":"train_valid_split","repo":"tliu1997/TI-SVM","repo_kind":"official","path":"EMNIST/DataLoader.py","file_url":"https://github.com/tliu1997/TI-SVM/blob/HEAD/EMNIST/DataLoader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4097b9b9d715cd45"}},{"code_sha256_prefix":"ef9857df09bc0e1c","entry":"train_valid_split","repo":"tliu1997/TI-SVM","repo_kind":"official","path":"MNIST/DataLoader.py","file_url":"https://github.com/tliu1997/TI-SVM/blob/HEAD/MNIST/DataLoader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef9857df09bc0e1c"}},{"code_sha256_prefix":"03b5869bf9171f94","entry":"translation_preprocess","repo":"tliu1997/TI-SVM","repo_kind":"official","path":"TMNIST/ImageUtils.py","file_url":"https://github.com/tliu1997/TI-SVM/blob/HEAD/TMNIST/ImageUtils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03b5869bf9171f94"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}