{"url":"/dataset/xysquares","name":"XYSquares","full_name":null,"description_markdown":"Synthetic dataset intended for benchmarking disentanglement frameworks.\r\n\r\nXYSquares is adversarial in nature; the distance between any two observations in the dataset is constant when measured using a pixel-wise distance function. It is usually impossible for VAE frameworks that use pixel-wise losses to disentangle this dataset.\r\n\r\nThe dataset is constructed from 3 non-overlapping red, green and blue squares that are each $8\\times8$ pixels in size. Each square can move along the $x$ and $y$ coordinates of an $8\\times8$ grid. The resulting images are $64\\times64$ pixels in size. With this construction the dataset has a total of 8 ground-truth factors for a total of $8^6 = 262144$ observations.","description_withheld":null,"homepage":"https://github.com/nmichlo/disent","introduced_date":"2022-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/data-overlap-a-prerequisite-for","title":"Overlooked Implications of the Reconstruction Loss for VAE Disentanglement","first_author":"Nathan Michlo","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Disentanglement","url":"/task/disentanglement","datasets_with_task":"/datasets/task/disentanglement"}],"languages":[],"variants":["XYSquares"],"data_loaders":[{"repo":"https://github.com/nmichlo/disent","url":"https://github.com/nmichlo/disent","frameworks":["pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}