Methods › Computer Vision › Instance Segmentation Models › Deep-MAC
Deep-MAC
Introduced by Vighnesh Birodkar et al. in The surprising impact of mask-head architecture on novel class segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Deep-MAC, or Deep Mask-heads Above CenterNet, is a type of anchor-free instance segmentation model based on 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.
For predicting bounding boxes, CenterNet outputs 3 tensors: (1) a class-specific 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.
For Deep-MAC, in parallel to the box-related prediction heads, we add a fourth pixel embedding branch P. For each bounding box b, we crop a region P_b from P corresponding to b via ROIAlign 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.
In 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, the authors add a 32 × 32 × 2 tensor holding normalized (x, y) coordinates relative to the bounding box b.
In Syntology 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.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- HiT-MAC · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='HiT-MAC') - Memory of Amortized Contexts (MAC) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Memory of Amortized Contexts (MAC)')
Origin paper of this answer, arXiv:2305.10854 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 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 (of 3 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “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)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “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.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 1 tagged papers has a Syntology run on record
Page 1 of 1: paper 1 of 1, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
The surprising impact of mask-head architecture on novel class segmentation 1 Apr 2021 · 3 repositories · arXiv:2104.00613
Tasks archive 2025-07-28
3 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Instance Segmentation | 1 |
| Segmentation | 1 |
| Semantic Segmentation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections