{"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/text-promptable-surgical-instrument","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","arxiv_id":"2306.09244","date":"2023-06-15","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"In this paper, we propose a novel text promptable surgical instrument segmentation approach to overcome challenges associated with diversity and differentiation of surgical instruments in minimally invasive surgeries. We redefine the task as text promptable, thereby enabling a more nuanced comprehension of surgical instruments and adaptability to new instrument types. Inspired by recent advancements in vision-language models, we leverage pretrained image and text encoders as our model backbone and design a text promptable mask decoder consisting of attention- and convolution-based prompting schemes for surgical instrument segmentation prediction. Our model leverages multiple text prompts for each surgical instrument through a new mixture of prompts mechanism, resulting in enhanced segmentation performance. Additionally, we introduce a hard instrument area reinforcement module to improve image feature comprehension and segmentation precision. Extensive experiments on several surgical instrument segmentation datasets demonstrate our model's superior performance and promising generalization capability. To our knowledge, this is the first implementation of a promptable approach to surgical instrument segmentation, offering significant potential for practical application in the field of robotic-assisted surgery. Code is available at https://github.com/franciszzj/TP-SIS.","url_abs":"https://arxiv.org/abs/2306.09244v3","url_pdf":"https://arxiv.org/pdf/2306.09244v3.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":"text-promptable-surgical-instrument","repo_url":"https://github.com/franciszzj/tp-sis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.09244","atlas_url":"https://app.syntology.ai/?focus=2306.09244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09244"}},"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":"deterministic:regex_extraction","url":"https://github.com/franciszzj/TP-SIS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/franciszzj/tp-sis","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_draft_wrong":2,"unverified":8},"by_repo_kind":{"listed":{"samples":18,"ran":10,"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":18,"samples":[{"code_sha256_prefix":"29bea1a18a0fa0d5","entry":"AttentionPool2d","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"29bea1a18a0fa0d5"}},{"code_sha256_prefix":"a7b37873fc97ada3","entry":"CoordConv","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a7b37873fc97ada3"}},{"code_sha256_prefix":"cbfc74d5e2d86824","entry":"MaskIoUProjector","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cbfc74d5e2d86824"}},{"code_sha256_prefix":"6e45cfd2cbf33fd8","entry":"PatchEmbedForHardExample","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"6e45cfd2cbf33fd8"}},{"code_sha256_prefix":"d7d8cf176ff5d320","entry":"Projector","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7d8cf176ff5d320"}},{"code_sha256_prefix":"6b2f6197cf865450","entry":"TransformerDecoder","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"6b2f6197cf865450"}},{"code_sha256_prefix":"3f54bb164fbff60b","entry":"TransformerDecoderLayer","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"3f54bb164fbff60b"}},{"code_sha256_prefix":"d1bb444eef3c0759","entry":"VisionTransformer","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1bb444eef3c0759"}},{"code_sha256_prefix":"dbfe3357dc25ca5f","entry":"conv_layer","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dbfe3357dc25ca5f"}},{"code_sha256_prefix":"89f9fd49ddec76ba","entry":"linear_layer","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"89f9fd49ddec76ba"}},{"code_sha256_prefix":"326e17096eb218fb","entry":"CLIP","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"326e17096eb218fb"}},{"code_sha256_prefix":"784f1df3c3e2ea58","entry":"CRIS","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"784f1df3c3e2ea58"}},{"code_sha256_prefix":"81af5d8d5099e161","entry":"FPN","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"81af5d8d5099e161"}},{"code_sha256_prefix":"036efdeb4674cff1","entry":"MaskedAutoencoderViT","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"036efdeb4674cff1"}},{"code_sha256_prefix":"4dc896241245fc34","entry":"ModifiedResNet","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"4dc896241245fc34"}},{"code_sha256_prefix":"285be96bc4c43f4a","entry":"build_model","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"285be96bc4c43f4a"}},{"code_sha256_prefix":"a2800893a4f89bff","entry":"convert_weights","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"a2800893a4f89bff"}},{"code_sha256_prefix":"1efe7864b0c0bbb9","entry":"mae_vit_base_patch16_dec512d8b","repo":"franciszzj/tp-sis","repo_kind":"listed","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.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":"1efe7864b0c0bbb9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}