{"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/diversified-in-domain-synthesis-with","title":"Diversified in-domain synthesis with efficient fine-tuning for few-shot classification","arxiv_id":"2312.03046","date":"2023-12-05","proceeding":null,"authors":["Victor G. Turrisi da Costa","Nicola Dall'Asen","Yiming Wang","Nicu Sebe","Elisa Ricci"],"abstract":"Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers involves augmenting the labelled samples with synthetic images created by state-of-the-art text-to-image generation models. Following this trend, we propose Diversified In-domain Synthesis with Efficient Fine-tuning (DISEF), a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. DISEF consists of two main components. First, we propose a novel text-to-image augmentation pipeline that, by leveraging the real samples and their rich semantics coming from an advanced captioning model, promotes in-domain sample diversity for better generalization. Second, we emphasize the importance of effective model fine-tuning in few-shot recognition, proposing to use Low-Rank Adaptation (LoRA) for joint adaptation of the text and image encoders in a Vision Language Model. We validate our method in ten different benchmarks, consistently outperforming baselines and establishing a new state-of-the-art for few-shot classification. Code is available at https://github.com/vturrisi/disef.","url_abs":"https://arxiv.org/abs/2312.03046v2","url_pdf":"https://arxiv.org/pdf/2312.03046v2.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":"diversified-in-domain-synthesis-with","repo_url":"https://github.com/vturrisi/disef","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-augmentation","task_name":"Image Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.03046","atlas_url":"https://app.syntology.ai/?focus=2312.03046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03046"}},"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/vturrisi/disef","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"88ec2296de41023f","entry":"accuracy_at_k","repo":"vturrisi/disef","repo_kind":"official","path":"fine-tune/src/utils/misc.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/fine-tune/src/utils/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88ec2296de41023f"}},{"code_sha256_prefix":"52321defb194c04d","entry":"load_image","repo":"vturrisi/disef","repo_kind":"official","path":"generation/synthetic_augmentation_pipeline.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/generation/synthetic_augmentation_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52321defb194c04d"}},{"code_sha256_prefix":"d8123d675f0b86f7","entry":"omegaconf_select","repo":"vturrisi/disef","repo_kind":"official","path":"fine-tune/src/utils/misc.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/fine-tune/src/utils/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8123d675f0b86f7"}},{"code_sha256_prefix":"a37d63f7ecc2e5c4","entry":"pad_image","repo":"vturrisi/disef","repo_kind":"official","path":"generation/synthetic_augmentation_pipeline.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/generation/synthetic_augmentation_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a37d63f7ecc2e5c4"}},{"code_sha256_prefix":"a00b191edbcbba19","entry":"weighted_mean","repo":"vturrisi/disef","repo_kind":"official","path":"fine-tune/src/utils/misc.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/fine-tune/src/utils/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a00b191edbcbba19"}},{"code_sha256_prefix":"c77c4aa4396ed626","entry":"pil_to_latents","repo":"vturrisi/disef","repo_kind":"official","path":"generation/synthetic_augmentation_pipeline.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/generation/synthetic_augmentation_pipeline.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":"c77c4aa4396ed626"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}