{"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/convnet-vs-transformer-supervised-vs-clip","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","arxiv_id":"2311.09215","date":"2023-11-15","proceeding":null,"authors":["Kirill Vishniakov","Zhiqiang Shen","Zhuang Liu"],"abstract":"Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are compared by their classification accuracy on ImageNet. However, this single metric does not fully capture performance nuances critical for specialized tasks. In this work, we conduct an in-depth comparative analysis of model behaviors beyond ImageNet accuracy, for both ConvNet and Vision Transformer architectures, each across supervised and CLIP training paradigms. Although our selected models have similar ImageNet accuracies and compute requirements, we find that they differ in many other aspects: types of mistakes, output calibration, transferability, and feature invariance, among others. This diversity in model characteristics, not captured by traditional metrics, highlights the need for more nuanced analysis when choosing among different models. Our code is available at https://github.com/kirill-vish/Beyond-INet.","url_abs":"https://arxiv.org/abs/2311.09215v3","url_pdf":"https://arxiv.org/pdf/2311.09215v3.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":"convnet-vs-transformer-supervised-vs-clip","repo_url":"https://github.com/kirill-vish/beyond-inet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"robust-classification","task_name":"Robust classification"},{"task_slug":"synthetic-image-attribution","task_name":"Synthetic Image Attribution"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"convnext","method_name":"ConvNeXt"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09215"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kirill-vish/beyond-inet","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"3eaa9b351b8b3a98","entry":"save_fig","repo":"kirill-vish/beyond-inet","repo_kind":"official","path":"inference/calibration.py","file_url":"https://github.com/kirill-vish/beyond-inet/blob/HEAD/inference/calibration.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3eaa9b351b8b3a98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}