Browse State-of-the-Art › Learning with coarse labels
Learning with coarse labels
5 papers with code · 4 benchmarks · 4 datasets archive 2025-07-28
Learning fine-grained representation with coarsely-labelled dataset, which can significantly reduce the labelling cost. As a simple example, for the task of differentiation between different pets, we need a knowledgeable cat lover to distinguish between ‘British short’ and ‘Siamese’, but even a child annotator may help to discriminate between ‘cat’ and ‘non-cat’.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 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 |
|---|---|---|---|---|---|
| cifar100 (2 rows) | MaskCon | MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset | code | Syntology ran 0 of 2 samples · 2 unverified | Compare |
| ImageNet32 (2 rows) | MaskCon | MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset | code | Syntology ran 0 of 2 samples · 2 unverified | Compare |
| Stanford Online Products (2 rows) | MaskCon | MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset | code | Syntology ran 0 of 2 samples · 2 unverified | Compare |
| Stanford Cars (2 rows) | MaskCon | MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset | code | Syntology ran 0 of 2 samples · 2 unverified | 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
4 datasets 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
5 shown of 5 papers with code (6 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 Feb 2025 1 repository listedThe Coarse-to-Fine Few-Shot (C2FS) task is designed to train models using only coarse labels, then leverages a limited number of subclass samples to achieve fine-grained recognition capabilities.
-
6 Aug 2023 1 repository listedIn the paper, we propose FocalSegNet, a novel 3D focal modulation UNet, to detect an aneurysm and offer an initial, coarse segmentation of it from time-of-flight MRA image patches, which is further refined with a dense…
-
22 Mar 2023 1 repository listed Syntology ran 0 of 2 samples · 2 unverifiedMore specifically, within the contrastive learning framework, for each sample our method generates soft-labels with the aid of coarse labels against other samples and another augmented view of the sample in question.
-
7 Dec 2020 1 repository listedA very practical example of C2FS is when the target classes are sub-classes of the training classes.
-
19 May 2020 1 repository listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available.
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