Papers › Where are the Blobs: Counting by Localization with Point Supervision

Where are the Blobs: Counting by Localization with Point Supervision

25 Jul 2018ECCV 2018 9arXiv:1807.09856archive 2025-07-28

Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro, David Vazquez, Mark Schmidt

Object counting is an important task in computer vision due to its growing demand in applications such as surveillance, traffic monitoring, and counting everyday objects. State-of-the-art methods use regression-based optimization where they explicitly learn to count the objects of interest. These often perform better than detection-based methods that need to learn the more difficult task of predicting the location, size, and shape of each object. However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods. Our contributions are three-fold: (1) we propose a novel loss function that encourages the network to output a single blob per object instance using point-level annotations only; (2) we design two methods for splitting large predicted blobs between object instances; and (3) we show that our method achieves new state-of-the-art results on several challenging datasets including the Pascal VOC and the Penguins dataset. Our method even outperforms those that use stronger supervision such as depth features, multi-point annotations, and bounding-box labels.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1807.09856")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: community (archive-listed): 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

CJLee94/Point-Supervised-Segmentation mentioned on GitHubpytorch report
ElementAI/LCFCN mentioned on GitHubpytorchApache-2.0 report
andohuman/RebarCounting mentioned on GitHubpytorch 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

12unverified

Licence: 0 of the 12 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 ElementAI/LCFCN. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

apply_transform ElementAI/LCFCN/src/datasets/transformers.py community (archive-listed) unverified Apache-2.0 (permissive) · 678428d62bcd23a4 · report
compute_loss ElementAI/LCFCN/lcfcn/lcfcn_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 2da876cd325bf204 · report
conv1x1 ElementAI/LCFCN/lcfcn/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 14ea4ddcb2e5ad11 · report
conv3x3 ElementAI/LCFCN/lcfcn/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · c04da432baaa4b0c · report
convert ElementAI/LCFCN/lcfcn/lcfcn.py community (archive-listed) unverified Apache-2.0 (permissive) · d23baf1bd67c5bc8 · report
get_tgt_list ElementAI/LCFCN/lcfcn/lcfcn_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 5ad9037903961e23 · report
get_upsampling_weight ElementAI/LCFCN/lcfcn/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 68f02849ad3eb678 · report
read_text ElementAI/LCFCN/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 6bb69822b71a0057 · report
shrink2roi ElementAI/LCFCN/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 87904dbbf17df380 · report
t2n ElementAI/LCFCN/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · e1c5e6dc7a97aa4b · report
transform_image ElementAI/LCFCN/lcfcn/lcfcn.py community (archive-listed) unverified Apache-2.0 (permissive) · ec5e6a234f9b03db · report
watersplit ElementAI/LCFCN/lcfcn/lcfcn_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 64c5b58a350a0950 · report

Tasks

ObjectObject Countingregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Counting COCO count-test LC-ResFCN m-reIRMSE 0.19 #4 of 7 Archive leaderboard report
Object Counting COCO count-test LC-ResFCN m-reIRMSE-nz 0.99 #4 of 7 Archive leaderboard report
Object Counting COCO count-test LC-ResFCN mRMSE 0.38 #4 of 7 Archive leaderboard report
Object Counting COCO count-test LC-ResFCN mRMSE-nz 2.20 #4 of 7 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-ResFCN m-reIRMSE-nz 0.61 #2 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-ResFCN m-relRMSE 0.17 #2 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-ResFCN mRMSE 0.31 #2 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-ResFCN mRMSE-nz 1.20 #2 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-PSPNet m-reIRMSE-nz 0.70 #5 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-PSPNet m-relRMSE 0.20 #5 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-PSPNet mRMSE 0.35 #5 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test LC-PSPNet mRMSE-nz 1.32 #5 of 8 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