Papers › CountGD: Multi-Modal Open-World Counting

CountGD: Multi-Modal Open-World Counting

5 Jul 2024arXiv:2407.04619archive 2025-07-28

Niki Amini-Naieni, Tengda Han, Andrew Zisserman

The goal of this paper is to improve the generality and accuracy of open-vocabulary object counting in images. To improve the generality, we repurpose an open-vocabulary detection foundation model (GroundingDINO) for the counting task, and also extend its capabilities by introducing modules to enable specifying the target object to count by visual exemplars. In turn, these new capabilities - being able to specify the target object by multi-modalites (text and exemplars) - lead to an improvement in counting accuracy. We make three contributions: First, we introduce the first open-world counting model, CountGD, where the prompt can be specified by a text description or visual exemplars or both; Second, we show that the performance of the model significantly improves the state of the art on multiple counting benchmarks - when using text only, CountGD is comparable to or outperforms all previous text-only works, and when using both text and visual exemplars, we outperform all previous models; Third, we carry out a preliminary study into different interactions between the text and visual exemplar prompts, including the cases where they reinforce each other and where one restricts the other. The code and an app to test the model are available at https://www.robots.ox.ac.uk/~vgg/research/countgd/.

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 9 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 9 samples from 2 repositories, 4 ran (4 with no instrument failure; 0 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.

niki-amini-naieni/CountGD mentioned on GitHubpytorchSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
niki-amini-naieni/countx mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 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

9 samples harvested: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

4ran
5unverified

Licence: 0 of the 9 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

niki-amini-naieni/CountGD community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
PositionalEncodingsFixed models/GroundingDINO/groundingdino.py ran MIT (permissive) · 9f204c85d112d40e · report fixture: returned PositionalEncodingsFixed · level recorded 2026-09-22
GroundingDINO models/GroundingDINO/groundingdino.py unverified MIT (permissive) · 52f493b1857ba9eb · report
TransformerEncoder in 96 papers models/GroundingDINO/groundingdino.py unverified MIT (permissive) · daf42163c5ae159d · report
TransformerEncoderLayer in 90 papers models/GroundingDINO/groundingdino.py unverified MIT (permissive) · 57469407352666b4 · report
niki-amini-naieni/countx community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
CrossAttention in 85 papers models_counting_network.py ran · metamorphic tier: invariant MIT (permissive) · 4cb253256cb32632 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
models_counting_network.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 59c07cf4d49e5e3c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Mlp in 102 papers models_counting_network.py ran · metamorphic tier: invariant MIT (permissive) · 6f6aa7aeb7d08957 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
CountingNetwork models_counting_network.py unverified MIT (permissive) · 7a6e35a004c4b745 · report
CrossAttentionBlock in 16 papers models_counting_network.py unverified MIT (permissive) · c0ab3335e60b739b · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for COUNTGD (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for COUNTGD (graph method: COUNTGD). 13 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GroundingDINO entry · level 0 · unverified · 52f493b1857ba9eb
  2. BertModelWarper helper · level 0 · unverified · 4cb5a39bc39dcd61
  3. ContrastiveEmbed helper · level 1 · ran · d5c391b32de453d0
  4. MLP helper · level 1 · ran · 4a5db0126fad661e
  5. NestedTensor helper · level 1 · ran · 8edcd8b335f324e7
  6. PositionalEncodingsFixed helper · level 1 · ran · 9f204c85d112d40e
  7. TransformerEncoder helper · level 0 · unverified · daf42163c5ae159d
  8. generate_masks_with_special_tokens_and_transfer_map helper · level 1 · ran; the contract check could not run · 10c7b3ef85aca8d6
  9. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94
  10. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 89899c07bc9d38f9
  11. TransformerEncoderLayer helper · level 0 · unverified · 57469407352666b4
  12. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  13. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 02f10894967515c7

harvested Assembly for COUNTGD (graph method: COUNTGD). 11 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. CountingNetwork entry · level 0 · unverified · 7a6e35a004c4b745
  2. CrossAttentionBlock model · level 0 · unverified · c0ab3335e60b739b
  3. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  4. Attention model · level 1 · ran · 9af3eb132594e510
  5. CrossAttention model · level 1 · ran · 4cb253256cb32632
  6. DropPath helper · level 1 · ran · 59c07cf4d49e5e3c
  7. Mlp model · level 1 · ran · 6f6aa7aeb7d08957
  8. drop_path helper · level 1 · ran; the contract check could not run · e3aa4e8e74369506
  9. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  10. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c
  11. _ntuple helper · level 1 · ran · our draft was wrong · 553ee0765abad219

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="2407.04619") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Object CountingOpen-vocabulary object countingZero-Shot Counting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Counting FSC147 CountGD MAE(test) 5.74 #1 of 19 Archive leaderboard report
Object Counting FSC147 CountGD MAE(val) 7.1 #1 of 19 Archive leaderboard report
Object Counting FSC147 CountGD RMSE(test) 24.09 #1 of 19 Archive leaderboard report
Object Counting FSC147 CountGD RMSE(val) 26.08 #1 of 19 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