{"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/describing-sets-of-images-with-textual-pca","title":"Describing Sets of Images with Textual-PCA","arxiv_id":"2210.12112","date":"2022-10-21","proceeding":null,"authors":["Oded Hupert","Idan Schwartz","Lior Wolf"],"abstract":"We seek to semantically describe a set of images, capturing both the attributes of single images and the variations within the set. Our procedure is analogous to Principle Component Analysis, in which the role of projection vectors is replaced with generated phrases. First, a centroid phrase that has the largest average semantic similarity to the images in the set is generated, where both the computation of the similarity and the generation are based on pretrained vision-language models. Then, the phrase that generates the highest variation among the similarity scores is generated, using the same models. The next phrase maximizes the variance subject to being orthogonal, in the latent space, to the highest-variance phrase, and the process continues. Our experiments show that our method is able to convincingly capture the essence of image sets and describe the individual elements in a semantically meaningful way within the context of the entire set. Our code is available at: https://github.com/OdedH/textual-pca.","url_abs":"https://arxiv.org/abs/2210.12112v1","url_pdf":"https://arxiv.org/pdf/2210.12112v1.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":"describing-sets-of-images-with-textual-pca","repo_url":"https://github.com/odedh/textual-pca","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.12112","atlas_url":"https://app.syntology.ai/?focus=2210.12112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12112"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/odedh/textual-pca","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"055b3d671ca7c0cb","entry":"calc_images_mean_embedding","repo":"odedh/textual-pca","repo_kind":"official","path":"customized_BLIP/semantic_pca_utils.py","file_url":"https://github.com/odedh/textual-pca/blob/HEAD/customized_BLIP/semantic_pca_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"055b3d671ca7c0cb"}},{"code_sha256_prefix":"2fce851e642435a0","entry":"principal_sentence_post_process","repo":"odedh/textual-pca","repo_kind":"official","path":"customized_BLIP/semantic_pca_utils.py","file_url":"https://github.com/odedh/textual-pca/blob/HEAD/customized_BLIP/semantic_pca_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fce851e642435a0"}},{"code_sha256_prefix":"e00864ab042325da","entry":"project_images_for_matching","repo":"odedh/textual-pca","repo_kind":"official","path":"customized_BLIP/semantic_pca_utils.py","file_url":"https://github.com/odedh/textual-pca/blob/HEAD/customized_BLIP/semantic_pca_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e00864ab042325da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}