Datasets › FSC147

FSC147

Introduced by Viresh Ranjan et al. in Learning To Count Everything16 Apr 2021 archive 2025-07-28

We introduce a dataset of 147 object categories containing over 6000 images that are suitable for the few-shot counting task. We collected and annotated images ourselves. Our dataset consists of 6135 images across a di- verse set of 147 object categories, from kitchen utensils and office stationery to vehicles and animals. The object count in our dataset varies widely, from 7 to 3731 objects, with an average count of 56 objects per image. In each image, each object instance is annotated with a dot at its approxi- mate center. In addition, three object instances are selected randomly as exemplar instances; these exemplars are also annotated with axis-aligned bounding boxes.

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

papers with a benchmark row: 22 · with a code link: 19 · where Syntology ran a sample: 7 (7 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (7 of 22 with a benchmark row: 7 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 22 of 22 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 58. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting 1 1 10 Feb 2025 not harvested
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation 1 3 27 Sep 2024 not harvested
GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting 0 2 18 Sep 2024 not harvested
CountGD: Multi-Modal Open-World Counting 2 1 5 Jul 2024 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
Learning Spatial Similarity Distribution for Few-shot Object Counting 1 1 20 May 2024 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (10 pointer-only for licence)
DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting 1 3 25 Apr 2024 official (archive's flag): 16 ran · 16 ran (of which 10 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
OmniCount: Multi-label Object Counting with Semantic-Geometric Priors 0 2 8 Mar 2024 not harvested
Point Segment and Count: A Generalized Framework for Object Counting 1 1 1 Jan 2024 not harvested
Semantic Generative Augmentations for Few-Shot Counting 1 2 26 Oct 2023 not harvested
Training-free Object Counting with Prompts 1 1 30 Jun 2023 not harvested
Open-world Text-specified Object Counting 1 1 2 Jun 2023 not harvested
Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting 1 1 8 May 2023 not harvested
Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting 1 1 21 Dec 2022 not harvested
A Low-Shot Object Counting Network With Iterative Prototype Adaptation 1 2 15 Nov 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
CounTR: Transformer-based Generalised Visual Counting 1 2 29 Aug 2022 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Few-shot Object Counting and Detection 1 2 22 Jul 2022 official (archive's flag): 4 ran · 4 ran (of which 0 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) · 0 unverified
Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision 2 2 20 May 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (2 pointer-only for licence)
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting 1 1 16 Mar 2022 official: harvested, nothing ran · 0 ran · 1 unverified
Few-shot Object Counting with Similarity-Aware Feature Enhancement 1 1 22 Jan 2022 not harvested
Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers 1 1 5 Jan 2022 not harvested
Object Counting: You Only Need to Look at One 0 1 11 Dec 2021 not harvested
Learning To Count Everything 1 2 16 Apr 2021 official: harvested, nothing ran · 0 ran · 1 unverified

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT LICENSE

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • FSC147

1 variant name, as the archive lists them.

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