{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/mask-attention-free-transformer-for-3d","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","arxiv_id":"2309.01692","date":"2023-09-04","proceeding":"ICCV 2023 1","authors":["Xin Lai","Yuhui Yuan","Ruihang Chu","Yukang Chen","Han Hu","Jiaya Jia"],"abstract":"Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively refine themselves in a similar manner. However, we observe that the mask-attention pipeline usually leads to slow convergence due to low-recall initial instance masks. Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead. Through center regression, we effectively overcome the low-recall issue and perform cross-attention by imposing positional prior. To reach this goal, we develop a series of position-aware designs. First, we learn a spatial distribution of 3D locations as the initial position queries. They spread over the 3D space densely, and thus can easily capture the objects in a scene with a high recall. Moreover, we present relative position encoding for the cross-attention and iterative refinement for more accurate position queries. Experiments show that our approach converges 4x faster than existing work, sets a new state of the art on ScanNetv2 3D instance segmentation benchmark, and also demonstrates superior performance across various datasets. Code and models are available at https://github.com/dvlab-research/Mask-Attention-Free-Transformer.","url_abs":"https://arxiv.org/abs/2309.01692v1","url_pdf":"https://arxiv.org/pdf/2309.01692v1.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":"mask-attention-free-transformer-for-3d","repo_url":"https://github.com/dvlab-research/mask-attention-free-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":null,"task_name":"Position"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-instance-segmentation-on-scannetv2","task":"3D Instance Segmentation","dataset":"ScanNet(v2)","model":"MAFT","rank_in_archive_order":32,"of":32,"metrics":{"mAP":"59.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.01692","atlas_url":"https://app.syntology.ai/?focus=2309.01692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01692"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.01692"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.01692"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.01692\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2309.01692"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.01692\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.01692"},"call":"get_concepts_for_paper(arxiv_id=\"2309.01692\")"}],"by_repo":[{"repo":"dvlab-research/mask-attention-free-transformer","kind":"official","samples":10,"ran":6,"instrument":3,"unverified":4}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2309.01692.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2309.01692.svg"},"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/dvlab-research/mask-attention-free-transformer","reach":{"status":"ok"}}],"summary":{"ran_fixture":3,"ran":2,"ran_honours":1,"unverified":4},"n_samples":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":10,"ran":6,"n_ran_checked":3,"n_instrument":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":10,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"89f8d423e0baf041","code_sha256_prefix":"89f8d423e0baf041","entry":"batch_dice_loss","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/loss.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/loss.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","code_page":"/code/batch-dice-loss","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"code_sha256":"b91d93c29e979019","code_sha256_prefix":"b91d93c29e979019","entry":"random_sampling","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/pc_util.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/pc_util.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pc:ndarray/2/float, num_sample:int/0/int, replace:NoneType/0/?, return_choices:bool/0/bool","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","code_page":"/code/random-sampling","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"b91d93c29e979019"}},{"code_sha256":"f8eff0243802706a","code_sha256_prefix":"f8eff0243802706a","entry":"rle_decode","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/utils/mask_encoder.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/utils/mask_encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"rle:dict/0/?","fixture_out_type":"ndarray","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/rle-decode","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"f8eff0243802706a"}},{"code_sha256":"6fdabd36a13625dd","code_sha256_prefix":"6fdabd36a13625dd","entry":"rle_encode","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/utils/mask_encoder.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/utils/mask_encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"mask:ndarray/1/int","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/rle-encode","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"6fdabd36a13625dd"}},{"code_sha256":"c2546a46c7f63930","code_sha256_prefix":"c2546a46c7f63930","entry":"scale_points","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/pc_util.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/pc_util.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"pred_xyz:Tensor/3/float, mult_factor:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"c2546a46c7f63930"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"c2546a46c7f63930"}},{"code_sha256":"818099bdffc93897","code_sha256_prefix":"818099bdffc93897","entry":"shift_scale_points","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/pc_util.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/pc_util.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"pred_xyz:Tensor/3/float, src_range:list/1/Tensor, dst_range:list/1/Tensor","fixture_out_type":"Tensor","code_page":"/code/shift-scale-points","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"818099bdffc93897"}},{"code_sha256":"2815d6704af5fb9c","code_sha256_prefix":"2815d6704af5fb9c","entry":"batch_sigmoid_bce_loss","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/loss.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/batch-sigmoid-bce-loss","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"2815d6704af5fb9c"}},{"code_sha256":"5ce41ce149ac0278","code_sha256_prefix":"5ce41ce149ac0278","entry":"batch_sigmoid_focal_loss","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/loss.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/batch-sigmoid-focal-loss","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"5ce41ce149ac0278"}},{"code_sha256":"31be13e9daaa9da9","code_sha256_prefix":"31be13e9daaa9da9","entry":"build_transformer","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/transformer.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/build-transformer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"31be13e9daaa9da9"}},{"code_sha256":"f09175b0f39f0ad0","code_sha256_prefix":"f09175b0f39f0ad0","entry":"multi_head_attention_forward","repo":"dvlab-research/mask-attention-free-transformer","repo_kind":"official","path":"maft/model/attention.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/multi-head-attention-forward","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dvlab-research/mask-attention-free-transformer when it was checked","mcp_get_code":{"code_sha256":"f09175b0f39f0ad0"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"69e8f8d8c528722ee2a7425ab7c6c8898234d5e574bf6c536f2c9df972e36ff3","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}