{"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/multi-perspective-data-augmentation-for-few","title":"Multi-Perspective Data Augmentation for Few-shot Object Detection","arxiv_id":"2502.18195","date":"2025-02-25","proceeding":null,"authors":["Anh-Khoa Nguyen Vu","Quoc-Truong Truong","Vinh-Tiep Nguyen","Thanh Duc Ngo","Thanh-Toan Do","Tam V. Nguyen"],"abstract":"Recent few-shot object detection (FSOD) methods have focused on augmenting synthetic samples for novel classes, show promising results to the rise of diffusion models. However, the diversity of such datasets is often limited in representativeness because they lack awareness of typical and hard samples, especially in the context of foreground and background relationships. To tackle this issue, we propose a Multi-Perspective Data Augmentation (MPAD) framework. In terms of foreground-foreground relationships, we propose in-context learning for object synthesis (ICOS) with bounding box adjustments to enhance the detail and spatial information of synthetic samples. Inspired by the large margin principle, support samples play a vital role in defining class boundaries. Therefore, we design a Harmonic Prompt Aggregation Scheduler (HPAS) to mix prompt embeddings at each time step of the generation process in diffusion models, producing hard novel samples. For foreground-background relationships, we introduce a Background Proposal method (BAP) to sample typical and hard backgrounds. Extensive experiments on multiple FSOD benchmarks demonstrate the effectiveness of our approach. Our framework significantly outperforms traditional methods, achieving an average increase of $17.5\\%$ in nAP50 over the baseline on PASCAL VOC. Code is available at https://github.com/nvakhoa/MPAD.","url_abs":"https://arxiv.org/abs/2502.18195v1","url_pdf":"https://arxiv.org/pdf/2502.18195v1.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":"multi-perspective-data-augmentation-for-few","repo_url":"https://github.com/nvakhoa/mpad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.18195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18195"}},"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/nvakhoa/MPAD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvakhoa/mpad","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran_fixture":1},"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":"747fa523e7e9b04b","entry":"get_features","repo":"nvakhoa/mpad","repo_kind":"official","path":"mpad_generation/main_generate_data.py","file_url":"https://github.com/nvakhoa/mpad/blob/HEAD/mpad_generation/main_generate_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"747fa523e7e9b04b"}},{"code_sha256_prefix":"fb6b23c08d77f532","entry":"prepare_mask_and_masked_image","repo":"nvakhoa/mpad","repo_kind":"official","path":"mpad_generation/PowerPaint/pipeline/pipeline_PowerPaint.py","file_url":"https://github.com/nvakhoa/mpad/blob/HEAD/mpad_generation/PowerPaint/pipeline/pipeline_PowerPaint.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb6b23c08d77f532"}},{"code_sha256_prefix":"aa76b8cfb627f945","entry":"torch_edit","repo":"nvakhoa/mpad","repo_kind":"official","path":"mpad_generation/utils/functions.py","file_url":"https://github.com/nvakhoa/mpad/blob/HEAD/mpad_generation/utils/functions.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"none","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa76b8cfb627f945"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}