{"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/image-free-classifier-injection-for-zero-shot","title":"Image-free Classifier Injection for Zero-Shot Classification","arxiv_id":"2308.10599","date":"2023-08-21","proceeding":"ICCV 2023 1","authors":["Anders Christensen","Massimiliano Mancini","A. Sophia Koepke","Ole Winther","Zeynep Akata"],"abstract":"Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from scratch with specialised methods: therefore, access to a training dataset is required when the need for zero-shot classification arises. In this paper, we aim to equip pre-trained models with zero-shot classification capabilities without the use of image data. We achieve this with our proposed Image-free Classifier Injection with Semantics (ICIS) that injects classifiers for new, unseen classes into pre-trained classification models in a post-hoc fashion without relying on image data. Instead, the existing classifier weights and simple class-wise descriptors, such as class names or attributes, are used. ICIS has two encoder-decoder networks that learn to reconstruct classifier weights from descriptors (and vice versa), exploiting (cross-)reconstruction and cosine losses to regularise the decoding process. Notably, ICIS can be cheaply trained and applied directly on top of pre-trained classification models. Experiments on benchmark ZSL datasets show that ICIS produces unseen classifier weights that achieve strong (generalised) zero-shot classification performance. Code is available at https://github.com/ExplainableML/ImageFreeZSL .","url_abs":"https://arxiv.org/abs/2308.10599v1","url_pdf":"https://arxiv.org/pdf/2308.10599v1.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":"image-free-classifier-injection-for-zero-shot","repo_url":"https://github.com/explainableml/imagefreezsl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.10599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10599"}},"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/explainableml/imagefreezsl","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ExplainableML/ImageFreeZSL","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"2eca1a3541f12c97","entry":"JOINT_AUTOENCODER","repo":"ExplainableML/ImageFreeZSL","repo_kind":"official","path":"utility/model_bases.py","file_url":"https://github.com/ExplainableML/ImageFreeZSL/blob/HEAD/utility/model_bases.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2eca1a3541f12c97"}},{"code_sha256_prefix":"02982209291b5ab9","entry":"prep_imagenet_vocab","repo":"explainableml/imagefreezsl","repo_kind":"official","path":"utility/load_wordembeddings.py","file_url":"https://github.com/explainableml/imagefreezsl/blob/HEAD/utility/load_wordembeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02982209291b5ab9"}},{"code_sha256_prefix":"246bd92f0f92ff4c","entry":"prepare_vocab","repo":"explainableml/imagefreezsl","repo_kind":"official","path":"utility/load_wordembeddings.py","file_url":"https://github.com/explainableml/imagefreezsl/blob/HEAD/utility/load_wordembeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"246bd92f0f92ff4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}