{"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/revisiting-few-shot-object-detection-with","title":"Revisiting Few-Shot Object Detection with Vision-Language Models","arxiv_id":"2312.14494","date":"2023-12-22","proceeding":null,"authors":["Anish Madan","Neehar Peri","Shu Kong","Deva Ramanan"],"abstract":"The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of \"open-world\" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot predictions from VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) on COCO. Despite their strong zero-shot performance, such foundation models may still be sub-optimal. For example, trucks on the web may be defined differently from trucks for a target application such as autonomous vehicle perception. We argue that the task of few-shot recognition can be reformulated as aligning foundation models to target concepts using a few examples. Interestingly, such examples can be multi-modal, using both text and visual cues, mimicking instructions that are often given to human annotators when defining a target concept of interest. Concretely, we propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external data and fine-tuned on multi-modal (text and visual) K-shot examples per target class. We repurpose nuImages for Foundational FSOD, benchmark several popular open-source VLMs, and provide an empirical analysis of state-of-the-art methods. Lastly, we discuss our recent CVPR 2024 Foundational FSOD competition and share insights from the community. Notably, the winning team significantly outperforms our baseline by 23.3 mAP! Our code and dataset splits are available at https://github.com/anishmadan23/foundational_fsod","url_abs":"https://arxiv.org/abs/2312.14494v4","url_pdf":"https://arxiv.org/pdf/2312.14494v4.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":"revisiting-few-shot-object-detection-with","repo_url":"https://github.com/anishmadan23/foundational_fsod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.14494","atlas_url":"https://app.syntology.ai/?focus=2312.14494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14494"}},"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/anishmadan23/foundational_fsod","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_violates":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"1f211df98dc51cee","entry":"get_clip_embeddings","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/predictor.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/predictor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f211df98dc51cee"}},{"code_sha256_prefix":"3b2a9d30d2f8d81a","entry":"get_fed_loss_inds_deterministic_with_negs","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/modeling/utils.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/modeling/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b2a9d30d2f8d81a"}},{"code_sha256_prefix":"e17a462624fc9dac","entry":"load_class_freq","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/modeling/utils.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/modeling/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e17a462624fc9dac"}},{"code_sha256_prefix":"c15434906f804d7f","entry":"match_name_keywords","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/custom_solver.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/custom_solver.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c15434906f804d7f"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/modeling/backbone/swintransformer.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/modeling/backbone/swintransformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/modeling/backbone/swintransformer.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/modeling/backbone/swintransformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"2e0a799ccbd489e7","entry":"compute_average_precision","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/evaluation/oideval.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/evaluation/oideval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2e0a799ccbd489e7"}},{"code_sha256_prefix":"3634f2208a0255d7","entry":"create_timm_resnet","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/modeling/backbone/timm.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/modeling/backbone/timm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3634f2208a0255d7"}},{"code_sha256_prefix":"c66a839ca35205e6","entry":"get_fed_loss_inds_deterministic2","repo":"anishmadan23/foundational_fsod","repo_kind":"official","path":"detic/modeling/utils.py","file_url":"https://github.com/anishmadan23/foundational_fsod/blob/HEAD/detic/modeling/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c66a839ca35205e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}