Exemplar-Free Counting

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 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.

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

8 shown of 8 papers with code (9 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.

• Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
  20 May 2022 2 repositories listed Syntology ran 1 of 5 samples · 4 unverified
  Specifically, we demonstrate that regression from vision transformer features without point-level supervision or reference images is superior to other reference-less methods and is competitive with methods that use…
• SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting
  10 Feb 2025 1 repository listed
  Zero-shot counting is a subcategory of Generic Visual Object Counting, which aims to count objects from an arbitrary class in a given image.
• A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
  27 Sep 2024 1 repository listed
  In addition, a novel counting loss is proposed, that directly optimizes the detection task and avoids the issues of the standard surrogate loss.
• DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting
  25 Apr 2024 1 repository listed Syntology ran 16 of 18 samples · 2 unverified
  DAVE 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…
• A Low-Shot Object Counting Network With Iterative Prototype Adaptation
  15 Nov 2022 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts.
• CounTR: Transformer-based Generalised Visual Counting
  29 Aug 2022 1 repository listed Syntology ran 1 of 4 samples · 3 unverified
  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…
• Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers
  5 Jan 2022 1 repository listed
  DisCOIL follows the basic principle of POC, but it adopts variational auto-encoders (VAE) instead of other well-established one-class classifiers (e.
• Learning To Count Everything
  16 Apr 2021 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  We also present a novel adaptation strategy to adapt our network to any novel visual category at test time, using only a few exemplar objects from the novel category.

Syntology lines on 5 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.