NIST · ИТ · df46933be1cd956255cb
Exact Tile-Based Segmentation Inference for Images Larger than GPU Memory
We address the problem of performing exact (tiling-error free) out-of-core semantic segmentation inference of arbitrarily large images using fully convolutional neural networks (FCN). FCN models have the property that once a model is trained, it can be
NIST · ИТОфициальный источник · 2021-06-03
{
"title_en": "Exact Tile-Based Segmentation Inference for Images Larger than GPU Memory",
"designation": "",
"series": "",
"status": "",
"date": "2021-06-03",
"date_original": "June 3, 2021",
"url": "https://www.nist.gov/publications/exact-tile-based-segmentation-inference-images-larger-gpu-memory",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Michael P. Majurski , Peter Bajcsy",
"abstract_excerpt_en": "We address the problem of performing exact (tiling-error free) out-of-core semantic segmentation inference of arbitrarily large images using fully convolutional neural networks (FCN). FCN models have the property that once a model is trained, it can be",
"id": "df46933be1cd956255cb",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Exact Tile-Based Segmentation Inference for Images Larger than GPU Memory",
"designation": "",
"series": "",
"status": "",
"date": "2021-06-03",
"date_original": "June 3, 2021",
"url": "https://www.nist.gov/publications/exact-tile-based-segmentation-inference-images-larger-gpu-memory",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Michael P. Majurski , Peter Bajcsy",
"abstract_excerpt_en": "We address the problem of performing exact (tiling-error free) out-of-core semantic segmentation inference of arbitrarily large images using fully convolutional neural networks (FCN). FCN models have the property that once a model is trained, it can be"
}
],
"translation_state": "none"
}