High-Resolution Subject Segmentation Entirely on Mobile NPUs: Exact Graph Rewrites, Split Resolution and 8-bit Distillation

Lumen Cutout is a subject segmentation model for phone NPUs. It starts from BiRefNet-lite, a high-resolution dichotomous segmentation model. With LiteRT and Qualcomm’s compiler, BiRefNet-lite does not compile to a phone NPU. Its decoder uses deformable convolutions, its Swin backbone uses tensors with five and six dimensions, and its shifted windows use a cyclic roll. Its full-resolution activations also do not fit the on-chip memory of the NPU. We change the model in three ways. First, we apply exact graph rewrites: four-dimensional window attention, roll-free shifted windows, channel-split convolutions and attention with one head at a time. Second, we change the architecture: plain convolutions in place of deformable ones, a backbone at 640 pixels with a mask at 1024 pixels from two inputs, a slim full-resolution tail, one global window in Swin stage 4, and no half-resolution backbone pass. Third, we train an all-8-bit model with quantization-aware distillation through the exact NPU graph. During this work we found that distillation silently disables the deepest branch of the decoder: its gate saturates at σ≈10−11, and the gradient cannot reopen it. We restore the branch from the teacher and keep it open with a feature loss. The final model computes a 1024×1024 mask in 23.7ms on a Snapdragon 8 Elite Gen 5 phone, in 31.1ms on a Snapdragon 8 Elite and in 182ms on a mid-range Snapdragon 7 Gen 1, with all 2,060 layers on the NPU. On the same phones, the original BiRefNet-lite does not fit in memory at 1024 pixels, and at 512 pixels it takes 677ms and 3,653ms on the CPU. The model compiles ahead of time for 42 Snapdragon chips as one NPU partition. Against the float BiRefNet-lite at 1024 pixels, its median IoU on the NPU is 0.993 on 150 held-out photos. Against human labels on ECSSD and DUT-OMRON, which neither model saw in training, the 8-bit model on the NPU matches its float teacher (S-measure 0.939 against 0.938 and 0.830 against 0.826), with slightly softer edges. On the fine structures of DIS-VD it loses 0.017 in S-measure. Among 17 public models and two platform APIs, it is second on ECSSD, after Apple Vision, and six models score higher on DUT-OMRON. We also show that the public BiRefNet-lite checkpoint was trained on the DIS5K test sets, and that a desktop CPU and the NPU rank two 8-bit quantization methods in opposite order. Model, weights and pipeline are open source.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24152779
Primary Topic
Advanced Neural Network Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

High-Resolution Subject Segmentation Entirely on Mobile NPUs: Exact Graph Rewrites, Split Resolution and 8-bit Distillation

Subhash Gottumukkala
Zenodo (CERN European Organization for Nuclear Research)
Advanced Neural Network Applications
preprint

High-Resolution Subject Segmentation Entirely on Mobile NPUs: Exact Graph Rewrites, Split Resolution and 8-bit Distillation

Subhash Gottumukkala
preprint en

Abstract

Lumen Cutout is a subject segmentation model for phone NPUs. It starts from BiRefNet-lite, a high-resolution dichotomous segmentation model. With LiteRT and Qualcomm’s compiler, BiRefNet-lite does not compile to a phone NPU. Its decoder uses deformable convolutions, its Swin backbone uses tensors with five and six dimensions, and its shifted windows use a cyclic roll. Its full-resolution activations also do not fit the on-chip memory of the NPU. We change the model in three ways. First, we apply exact graph rewrites: four-dimensional window attention, roll-free shifted windows, channel-split convolutions and attention with one head at a time. Second, we change the architecture: plain convolutions in place of deformable ones, a backbone at 640 pixels with a mask at 1024 pixels from two inputs, a slim full-resolution tail, one global window in Swin stage 4, and no half-resolution backbone pass. Third, we train an all-8-bit model with quantization-aware distillation through the exact NPU graph. During this work we found that distillation silently disables the deepest branch of the decoder: its gate saturates at σ≈10−11, and the gradient cannot reopen it. We restore the branch from the teacher and keep it open with a feature loss. The final model computes a 1024×1024 mask in 23.7ms on a Snapdragon 8 Elite Gen 5 phone, in 31.1ms on a Snapdragon 8 Elite and in 182ms on a mid-range Snapdragon 7 Gen 1, with all 2,060 layers on the NPU. On the same phones, the original BiRefNet-lite does not fit in memory at 1024 pixels, and at 512 pixels it takes 677ms and 3,653ms on the CPU. The model compiles ahead of time for 42 Snapdragon chips as one NPU partition. Against the float BiRefNet-lite at 1024 pixels, its median IoU on the NPU is 0.993 on 150 held-out photos. Against human labels on ECSSD and DUT-OMRON, which neither model saw in training, the 8-bit model on the NPU matches its float teacher (S-measure 0.939 against 0.938 and 0.830 against 0.826), with slightly softer edges. On the fine structures of DIS-VD it loses 0.017 in S-measure. Among 17 public models and two platform APIs, it is second on ECSSD, after Apple Vision, and six models score higher on DUT-OMRON. We also show that the public BiRefNet-lite checkpoint was trained on the DIS5K test sets, and that a desktop CPU and the NPU rank two 8-bit quantization methods in opposite order. Model, weights and pipeline are open source.

Zenodo (CERN European Organization for Nuclear Research)
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon