Papers › CounTR: Transformer-based Generalised Visual Counting

CounTR: Transformer-based Generalised Visual Counting

29 Aug 2022arXiv:2208.13721archive 2025-07-28

Chang Liu, Yujie Zhong, Andrew Zisserman, Weidi Xie

In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i.e. zero-shot or few-shot counting. To this end, we make the following four contributions: (1) We introduce a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given "exemplars" with the attention mechanism;(2) We adopt a two-stage training regime, that first pre-trains the model with self-supervised learning, and followed by supervised fine-tuning;(3) We propose a simple, scalable pipeline for synthesizing training images with a large number of instances or that from different semantic categories, explicitly forcing the model to make use of the given "exemplars";(4) We conduct thorough ablation studies on the large-scale counting benchmark, e.g. FSC-147, and demonstrate state-of-the-art performance on both zero and few-shot settings.

PaperPDFCodeCode 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="2208.13721")

Code

Syntology Ran 1 of 4 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 4 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Verg-Avesta/CounTR officialmentioned on GitHubpytorchMIT 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

4 samples harvested; 1 ran; 0 honoured the contract we drafted; 3 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.

1ran · fixture could not drive it
3unverified

Licence: 0 of the 4 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 Verg-Avesta/CounTR. “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.

drop_path Verg-Avesta/CounTR/models_crossvit.py official repository ran · fixture could not drive it MIT (permissive) · e3aa4e8e74369506 · report
load_image Verg-Avesta/CounTR/demo_zero.py official repository unverified MIT (permissive) · 1f53c50f46429972 · report
transform_pre_train Verg-Avesta/CounTR/util/FSC147.py official repository unverified MIT (permissive) · b3dfc95b707288c3 · report
transform_val Verg-Avesta/CounTR/util/FSC147.py official repository unverified MIT (permissive) · 75f6c7e715903362 · report

Tasks

Exemplar-Free CountingObject CountingSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Exemplar-Free Counting FSC147 CounTR MAE(test) 14.71 #4 of 9 Archive leaderboard report
Exemplar-Free Counting FSC147 CounTR MAE(val) 18.07 #4 of 9 Archive leaderboard report
Exemplar-Free Counting FSC147 CounTR RMSE(test) 106.87 #4 of 9 Archive leaderboard report
Exemplar-Free Counting FSC147 CounTR RMSE(val) 71.84 #4 of 9 Archive leaderboard report
Object Counting CARPK CounTR MAE 5.75 #4 of 15 Archive leaderboard report
Object Counting CARPK CounTR RMSE 7.45 #4 of 15 Archive leaderboard report
Object Counting FSC147 CounTR MAE(test) 11.95 #8 of 19 Archive leaderboard report
Object Counting FSC147 CounTR MAE(val) 13.13 #8 of 19 Archive leaderboard report
Object Counting FSC147 CounTR RMSE(test) 91.23 #8 of 19 Archive leaderboard report
Object Counting FSC147 CounTR RMSE(val) 49.83 #8 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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