{"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":"/method/deep-mac","slug":"deep-mac","name":"Deep-MAC","full_name":"Deep-MAC","full_name_withheld":false,"description_markdown":"**Deep-MAC**, or **Deep Mask-heads Above CenterNet**, is a type of anchor-free instance segmentation model based on [CenterNet](https://paperswithcode.com/method/centernet).  The motivation for this new architecture is that boxes are much cheaper to annotate than masks, so the authors address the “partially supervised” instance segmentation problem, where all classes have bounding box annotations but only a subset of classes have mask annotations. \r\n\r\nFor predicting bounding boxes, CenterNet outputs 3 tensors: (1) a class-specific [heatmap](https://paperswithcode.com/method/heatmap) which indicates the probability of the center of a bounding box being present at each location, (2) a class-agnostic 2-channel tensor indicating the height and width of the bounding box at each center pixel, and (3) since the output feature map is typically smaller than the image (stride 4 or 8), CenterNet also predicts an x and y direction offset to recover this discretization error at each center pixel.\r\n\r\nFor Deep-MAC, in parallel to the box-related prediction heads, we add a fourth pixel embedding branch $P$. For each bounding box\r\n$b$, we crop a region $P\\_{b}$ from $P$ corresponding to $b$ via [ROIAlign](https://paperswithcode.com/method/roi-align) which results in a 32 × 32 tensor. We then feed each $P\\_{b}$ to a mask-head. The final prediction at the end is a class-agnostic 32 × 32 tensor which we pass through a sigmoid to get per-pixel probabilities. We train this mask-head via a per-pixel cross-entropy loss averaged over all pixels and instances. During post-processing, the predicted mask is re-aligned according to the predicted box and resized to the resolution of the image. \r\n\r\nIn addition to this 32 × 32 cropped feature map, we add two inputs for improved stability of some mask-heads: (1) Instance embedding: an additional head is added to the backbone that predicts a per-pixel embedding. For each bounding box $b$ we extract its embedding from the center pixel. This embedding is tiled to a size of 32 × 32 and concatenated to the pixel embedding crop. This helps condition the mask-head on a particular instance and disambiguate it from others. (2) Coordinate Embedding: Inspired by [CoordConv](https://paperswithcode.com/method/coordconv), the authors add a 32 × 32 × 2 tensor holding normalized $\\left(x, y\\right)$ coordinates relative to the bounding box $b$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"The surprising impact of mask-head architecture on novel class segmentation","paper":"/paper/the-surprising-impact-of-mask-head","first_author":"Vighnesh Birodkar","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/the-surprising-impact-of-mask-head"},"source":{"url":"https://arxiv.org/abs/2104.00613v2","title":"The surprising impact of mask-head architecture on novel class segmentation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Instance Segmentation Models","url":"/methods/category/instance-segmentation-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/the-surprising-impact-of-mask-head","slug":"the-surprising-impact-of-mask-head","title":"The surprising impact of mask-head architecture on novel class segmentation","date":"2021-04-01","arxiv_id":"2104.00613","n_code_links":3,"syntology":null}],"papers_shown":1,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deep-mac"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Deep-MAC","read_at":"2026-10-05T00:54:36+00:00","query":"Deep-MAC","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"MAC","origin_arxiv_id":"2305.10854"},"resolution":"token_match","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2104.00613","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2305.10854","citations":206},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Deep-MAC'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[{"name":"HiT-MAC","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":2,"retrieve_with":"get_reference_implementation(name='HiT-MAC')","origin_arxiv_id":"2010.13110"},{"name":"Memory of Amortized Contexts (MAC)","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":3,"retrieve_with":"get_reference_implementation(name='Memory of Amortized Contexts (MAC)')","origin_arxiv_id":"2403.04317"}],"code_nearby_caption":"Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.","origin_paper":{"arxiv_id":"2305.10854","page":"/paper/3d-registration-with-maximal-cliques-1","syntology_url":"https://syntology.ai/paper/2305.10854","in_graph_layer":true,"samples":3,"ran":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"for a different name, 'MAC', about another paper, arXiv:2305.10854: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'MAC' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2305.10854, while the archive credits arXiv:2104.00613.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"e4eabe2a847140bf73679834d1769c9fb2062184f0ff9247cc1ab5fdb6af7fc9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}