Browse State-of-the-Art › Few-shot Object Counting and Detection
Few-shot Object Counting and Detection
4 papers with code · 2 benchmarks · 1 dataset archive 2025-07-28
Few-shot Object Counting and Detection aims to count and detect instances of objects of the same class as given exemplars within a single image, using only up to three exemplars from the original FSC147. This task is especially challenging but crucial when large datasets are unavailable. Methods for this task must output a single set of bounding boxes, from which the final count is derived based on the number of detected boxes.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| FSC147 (4 rows) | GeCo | A Novel Unified Architecture for Low-Shot Counting by Detection... | code | — | Compare |
| Zero Shot Counting on FSC147 (1 row) | SAVE | SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Most implemented papers archive 2025-07-28
4 shown of 4 papers with code (4 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
27 Sep 2024 1 repository listedIn addition, a novel counting loss is proposed, that directly optimizes the detection task and avoids the issues of the standard surrogate loss.
-
25 Apr 2024 1 repository listed Syntology ran 16 of 18 samples · 2 unverifiedDAVE outperforms the top density-based counters by ~20% in the total count MAE, it outperforms the most recent detection-based counter by ~20% in detection quality and sets a new state-of-the-art in zero-shot as well as…
-
1 Jan 2024 1 repository listedIn this paper we propose a generalized framework for both few-shot and zero-shot object counting based on detection.
-
22 Jul 2022 1 repository listed Syntology ran 0 of 4 samples · 4 unverifiedWe tackle a new task of few-shot object counting and detection.
Syntology lines on 2 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.
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