{"url":"/dataset/foodseg103","name":"FoodSeg103","full_name":"lewisnjue","description_markdown":"**FoodSeg103** is a new food image dataset containing 7,118 images. Images are annotated with 104 ingredient classes and each image has an average of 6 ingredient labels and pixel-wise masks. It's provided as a large-scale benchmark for food image segmentation.\r\n\r\nMajor Challenges:\r\n\r\n1. High intra-variance of the same food ingredient with different cooking methods\r\n2. Long-tail distribution\r\n3. Complicated contexts\r\n\r\nImage source: [https://arxiv.org/pdf/2105.05409v1.pdf](https://arxiv.org/pdf/2105.05409v1.pdf)","description_withheld":null,"homepage":"https://xiongweiwu.github.io/foodseg103.html","introduced_date":"2021-05-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-large-scale-benchmark-for-food-image","title":"A Large-Scale Benchmark for Food Image Segmentation","first_author":"Xiongwei Wu","url":null},"license":{"name":"Apache License 2.0","url":"https://github.com/XiongweiWu/FoodSeg-Benchmark/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FoodSeg103"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-foodseg103","task":"Semantic Segmentation","dataset_variant":"FoodSeg103","rows":7,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"FoodSAM","paper":"/paper/foodsam-any-food-segmentation","metrics":{"mIoU":"46.4"},"code_links":[{"title":"jamesjg/foodsam","url":"https://github.com/jamesjg/foodsam"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/foodsam-any-food-segmentation","title":"FoodSAM: Any Food Segmentation","date":"2023-08-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-large-scale-benchmark-for-food-image","title":"A Large-Scale Benchmark for Food Image Segmentation","date":"2021-05-12","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","rows_on_this_dataset":1,"code_links":80,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":207,"samples_ran":108,"samples_unverified":99,"pointer_only_for_licence":43,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-semantic-segmentation-from-a","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","date":"2020-12-31","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/ccnet-criss-cross-attention-for-semantic","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","date":"2018-11-28","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":9,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":224,"samples_ran":119,"samples_unverified":105,"pointer_only_for_licence":43,"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."}