Papers › CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

27 Feb 2018CVPR 2018 6arXiv:1802.10062archive 2025-07-28

Yuhong Li, Xiaofan Zhang, Deming Chen

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations. CSRNet is an easy-trained model because of its pure convolutional structure. We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF_CC_50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance. In the ShanghaiTech Part_B dataset, CSRNet achieves 47.3% lower Mean Absolute Error (MAE) than the previous state-of-the-art method. We extend the targeted applications for counting other objects, such as the vehicle in TRANCOS dataset. Results show that CSRNet significantly improves the output quality with 15.4% lower MAE than the previous state-of-the-art approach.

PaperPDFConference PDFCodeCode Syntology ran

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 15 code samples harvested from 4 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 4 repositories, 13 ran (12 with no instrument failure; 1 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Bazingaliu/learning_CSRNet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
CommissarMa/CSRNet-pytorch mentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (1 instrument-failed) · 0 unverified report
DiaoXY/CSRnet mentioned on GitHubtfSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
Neerajj9/CSRNet-keras mentioned on GitHubtfMITSyntology: not harvested report
RTalha/CROWD-COUNTING-USING-CSRNET mentioned on GitHubtfSyntology: not harvested report
Saritus/Crowd-Counter mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
dattatrayshinde/oc_sd mentioned on GitHubpytorchSyntology: not harvested report
karanjsingh/Improved-CSRNet mentioned on GitHubtfSyntology: not harvested report
krutikabapat/Crowd_Counting mentioned on GitHubSyntology: not harvested report
leeyeehoo/CSRNet-pytorch mentioned on GitHubpytorchSyntology: not harvested report
xr0927/chapter5-learning_CSRNet mentioned on GitHubpytorchSyntology: not harvested 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 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 · honoured contract
1ran · violated contract
1ran · our draft was wrong
8ran
2unverified

Licence: 6 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 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.

Bazingaliu/learning_CSRNet community (archive-listed) 1 sample, 0 ran · 1 unverified
gaussian_filter_density make_dataset.py unverified no licence file found · pointer only · b58a2ec6960d759c · report
CommissarMa/CSRNet-pytorch community (archive-listed) 7 samples, 7 ran (1 instrument-failed) · 0 unverified
create_test_dataloader dataset.py ran MIT (permissive) · 699624a8df54b1f2 · report fixture: signature root:str/0/str · returned DataLoader · level recorded 2026-09-26
create_train_dataloader dataset.py ran MIT (permissive) · 804f70b76bd6432b · report fixture: signature root:str/0/str, use_flip:bool/0/bool, batch_size:int/0/int · returned DataLoader · level recorded 2026-09-26
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
utils.py ran fingerprinted MIT (permissive) · c0c074850363dcfc · report fixture: signature tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-26
generate_fixed_kernel_densitymap data_preparation/dmap_for_SHHB.py ran MIT (permissive) · d78d232773b61dc2 · report fixture: signature image:ndarray/3/int, points:ndarray/2/float, sigma:int/0/int · returned ndarray · level recorded 2026-09-26
generate_k_nearest_kernel_densitymap data_preparation/dmap_for_SHHA.py ran MIT (permissive) · 5448b1b07af1f412 · report fixture: signature image:ndarray/3/int, points:ndarray/2/float · returned ndarray · level recorded 2026-09-26
generate_perspective_densitymap data_preparation/dmap_for_MALL.py ran fingerprinted MIT (permissive) · 5c608855cf4b96b9 · report fixture: signature image:ndarray/2/float, points:ndarray/2/float, p_map:ndarray/2/float · returned ndarray · level recorded 2026-09-26
make_layers in 155 papers model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · bd14ee2717325fe2 · report fixture: signature cfg:list/1/int, in_channels:int/0/int, batch_norm:bool/0/bool, dilation:bool/0/bool · returned Sequential · level recorded 2026-09-22
DiaoXY/CSRnet community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
create_img Model.py ran · honoured contract no licence file found · pointer only · ce39b03640271550 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-22
create_img Inference.py ran · honoured contract no licence file found · pointer only · 26d3609a29bca3ac · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-22
gaussian_filter_density Preprocess.py ran · violated contract fingerprinted no licence file found · pointer only · 78634a059bd32f30 · report fixture: signature gt:ndarray/2/float · returned ndarray · level recorded 2026-09-22
get_input in 20 papers Model.py ran · honoured contract no licence file found · pointer only · 70f82265ce8e8a4e · report fixture: signature path:list/1/str · returned ndarray · level recorded 2026-09-22
Saritus/Crowd-Counter community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
read_file_header mat4conda.py ran MIT (permissive) · ee85fe0942254f17 · report fixture: signature fd:BytesIO/0/?, endian:str/0/str · returned dict · level recorded 2026-09-26
unpack in 18 papers mat4conda.py ran MIT (permissive) · 0deef73b258cd476 · report fixture: returned bytes · level recorded 2026-09-26
diff in 16 papers mat4conda.py unverified MIT (permissive) · 2e7c732fa310801f · report

Tasks

Crowd CountingScene Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Crowd Counting ShanghaiTech A CSRNet MAE 68.2 #24 of 35 Archive leaderboard report
Crowd Counting ShanghaiTech B CSRNet MAE 10.6 #22 of 32 Archive leaderboard report
Crowd Counting TRANCOS CSRNet MAE 3.56 #4 of 4 Archive leaderboard report
Crowd Counting UCF CC 50 CSRNet MAE 266.1 #12 of 22 Archive leaderboard report
Crowd Counting Venice CSRNet MAE 35.8 #3 of 5 Archive leaderboard report
Crowd Counting WorldExpo’10 CSRNet Average MAE 8.6 #7 of 15 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