{
  "annotation_id": "29e91571-4c99-4fe8-a553-0c3aa5cbf4b3",
  "date_created": "2026-02-17T05:53:05.064000Z",
  "date_modified": "2026-02-17T05:53:05.064000Z",
  "file_hash": "3bd12729cd701b1e0e55eb5c18ee0e11cdb8ded9d5e3ba39a0a9976cf3045ca1",
  "private": false,
  "record": {
    "abstract": "Current approaches for segmenting ultra high resolution images either slide a window, thereby discarding global context, or downsample and lose fine detail. We propose a simple yet effective method that brings explicit multi scale reasoning to vision transformers, simultaneously preserving local details and global awareness. Concretely, we process each image in parallel at a local scale (high resolution, small crops) and a global scale (low resolution, large crops), and aggregate and propagate features between the two branches with a small set of learnable relay tokens. The design plugs directly into standard transformer backbones (eg ViT and Swin) and adds fewer than 2 % parameters. Extensive experiments on three ultra high resolution segmentation benchmarks, Archaeoscape, URUR, and Gleason, and on the conventional Cityscapes dataset show consistent gains, with up to 15 % relative mIoU improvement. Code and pretrained models are available at https://archaeoscape.ai/work/relay-tokens/ .",
    "arxiv_id": "2601.05927",
    "authors": [
      "Yohann Perron",
      "Vladyslav Sydorov",
      "Christophe Pottier",
      "Loic Landrieu"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Adapting Vision Transformers to Ultra-High Resolution Semantic Segmentation with Relay Tokens",
    "url": "https://arxiv.org/abs/2601.05927",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "2cf72c1a-08d5-4058-bf8a-ead6931b4104",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}