Papers › DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition

DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition

6 Jul 2022arXiv:2207.02606archive 2025-07-28

Matej Grcić, Petra Bevandić, Siniša Šegvić

Anomaly detection can be conceived either through generative modelling of regular training data or by discriminating with respect to negative training data. These two approaches exhibit different failure modes. Consequently, hybrid algorithms present an attractive research goal. Unfortunately, dense anomaly detection requires translational equivariance and very large input resolutions. These requirements disqualify all previous hybrid approaches to the best of our knowledge. We therefore design a novel hybrid algorithm based on reinterpreting discriminative logits as a logarithm of the unnormalized joint distribution p̂(x, y). Our model builds on a shared convolutional representation from which we recover three dense predictions: i) the closed-set class posterior P(y|x), ii) the dataset posterior P(dᵢₙ|x), iii) unnormalized data likelihood p̂(x). The latter two predictions are trained both on the standard training data and on a generic negative dataset. We blend these two predictions into a hybrid anomaly score which allows dense open-set recognition on large natural images. We carefully design a custom loss for the data likelihood in order to avoid backpropagation through the untractable normalizing constant Z(θ). Experiments evaluate our contributions on standard dense anomaly detection benchmarks as well as in terms of open-mIoU - a novel metric for dense open-set performance. Our submissions achieve state-of-the-art performance despite neglectable computational overhead over the standard semantic segmentation baseline.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

matejgrcic/DenseHybrid officialmentioned on GitHubpytorchSyntology: 13 samples, 12 ran (3 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
9ran
1unverified

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from matejgrcic/DenseHybrid. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

matejgrcic/DenseHybrid official repository 13 samples, 12 ran (3 instrument-failed) · 1 unverified
DenseNet in 5 papers models/ladder_densenet.py ran · metamorphic tier: deterministic fingerprinted GPL-2.0 (copyleft) · pointer only · 82fa155ecf7dd6ea · report fixture: returned DenseNet · level recorded 2026-09-22
SPPWrapper models/ladder_densenet.py ran · metamorphic tier: deterministic GPL-2.0 (copyleft) · pointer only · ff8e4e3cca125ab7 · report fixture: returned SPPWrapper · level recorded 2026-09-22
SpatialPyramidPooling models/ladder_densenet.py ran GPL-2.0 (copyleft) · pointer only · 670a3be43c04c03c · report fixture: returned SpatialPyramidPooling · level recorded 2026-09-22
UpsampleWrapper models/ladder_densenet.py ran · metamorphic tier: deterministic GPL-2.0 (copyleft) · pointer only · 829101d62a45513f · report fixture: returned UpsampleWrapper · level recorded 2026-09-22
_BNReluConv models/ladder_densenet.py ran · metamorphic tier: deterministic GPL-2.0 (copyleft) · pointer only · 4eb447fe1facaf64 · report fixture: returned _BNReluConv · level recorded 2026-09-22
_DenseBlock models/ladder_densenet.py ran · metamorphic tier: deterministic fingerprinted GPL-2.0 (copyleft) · pointer only · 78a6b14acf189d64 · report fixture: returned _DenseBlock · level recorded 2026-09-22
_DenseLayer models/ladder_densenet.py ran · metamorphic tier: deterministic GPL-2.0 (copyleft) · pointer only · 7590cc05fbd0178e · report fixture: returned _DenseLayer · level recorded 2026-09-22
_Transition models/ladder_densenet.py ran · metamorphic tier: deterministic GPL-2.0 (copyleft) · pointer only · 1c790b909fc8f0d1 · report fixture: returned _Transition · level recorded 2026-09-22
_Upsample models/ladder_densenet.py ran GPL-2.0 (copyleft) · pointer only · 378890a5c1832284 · report fixture: returned _Upsample · level recorded 2026-09-22
_checkpoint_bnreluconv models/ladder_densenet.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 39fa24f2290ebbd3 · report fixture: signature bn:callable/0/?, relu:callable/0/?, conv:callable/0/? · returned function · level recorded 2026-09-22
_checkpoint_transition models/ladder_densenet.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · a6df25fb24ddf178 · report fixture: signature norm:callable/0/?, relu:callable/0/?, conv:callable/0/?, pool:callable/0/? · returned function · level recorded 2026-09-22
_checkpoint_unit models/ladder_densenet.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 9e15f680fc14dc9e · report fixture: signature bn1:callable/0/?, relu1:callable/0/?, conv1:callable/0/?, bn2:callable/0/?, relu2:callable/0/?, conv2:callable/0/? · returned function · level recorded 2026-09-22
LadderDenseNet models/ladder_densenet.py unverified GPL-2.0 (copyleft) · pointer only · 77e4e57e31f33c48 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DenseHybrid (graph method: DenseHybrid). 13 bricks; individually on a fixture: 12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. LadderDenseNet entry · level 0 · unverified · 77e4e57e31f33c48
  2. DenseNet model · level 1 · ran · 82fa155ecf7dd6ea
  3. SPPWrapper model · level 1 · ran · ff8e4e3cca125ab7
  4. UpsampleWrapper model · level 1 · ran · 829101d62a45513f
  5. _BNReluConv model · level 1 · ran · 4eb447fe1facaf64
  6. _DenseBlock model · level 1 · ran · 78a6b14acf189d64
  7. _Transition model · level 1 · ran · 1c790b909fc8f0d1
  8. SpatialPyramidPooling model · level 1 · ran · 670a3be43c04c03c
  9. _Upsample model · level 1 · ran · 378890a5c1832284
  10. _checkpoint_bnreluconv helper · level 1 · ran · our draft was wrong · 39fa24f2290ebbd3
  11. _DenseLayer model · level 1 · ran · 7590cc05fbd0178e
  12. _checkpoint_transition helper · level 1 · ran · our draft was wrong · a6df25fb24ddf178
  13. _checkpoint_unit helper · level 1 · ran · our draft was wrong · 9e15f680fc14dc9e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2207.02606") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Anomaly DetectionOpen Set LearningScene SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Fishyscapes DenseHybrid AP 72.3 #5 of 8 Archive leaderboard report
Anomaly Detection Fishyscapes DenseHybrid FPR95 5.5 #5 of 8 Archive leaderboard report
Anomaly Detection Fishyscapes L&F DenseHybrid AP 43.9 #8 of 18 Archive leaderboard report
Anomaly Detection Fishyscapes L&F DenseHybrid FPR95 6.2 #8 of 18 Archive leaderboard report
Scene Segmentation StreetHazards LDN121-DenseHybrid Open-mIoU 45.8 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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