Browse State-of-the-Art › Unsupervised Part Discovery
Unsupervised Part Discovery
4 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Machine learning methods designed for unsupervised part discovery aim to identify a small number of semantically consistent parts, typically around (K=8), shared among classes in a dataset. These methods visualize all discovered parts in an image through per-part saliency maps, facilitating easier interpretation. However, as this task is unsupervised, it often relies on assumptions about the discovered parts, such as their distribution and shape.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
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
No dataset record in the archive lists this task.
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 (7 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.
-
15 Aug 2024 1 repository listedObject parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks.
-
5 Jul 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverifiedComputer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models.
-
11 Nov 2021 1 repository listedFirst, we construct a proxy task through a set of objectives that encourages the model to learn a meaningful decomposition of the image into its parts.
-
9 Sep 2020 1 repository listedOur approach leverages a generative model consisting of two disentangled representations for an object's shape and appearance and a latent variable for the part segmentation.
Syntology lines on 1 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