# Native Segmentation Vision Transformers

Source: [Native Segmentation Vision Transformers](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d7d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:44:13.662Z

Authors: Guillem Bras\\'o, Aljo\\v{s}a O\\v{s}ep, Laura Leal-Taix\\'e

Published: 2025-05-22T17:55:20.000Z

## Abstract

Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a reduced set based on image boundaries and their semantic content. Stacking our grouping layer across consecutive backbone stages results in hierarchical segmentation that arises natively in the feature extraction process, resulting in our coined Native Segmentation Vision Transformer. We show that a careful design of our architecture enables the emergence of strong segmentation masks solely from grouping layers, that is, without additional segmentation-specific heads. This sets the foundation for a new paradigm of native, backbone-level segmentation, which enables strong zero-shot results without mask supervision, as well as a minimal and efficient standalone model design for downstream segmentation tasks. Our project page is https://research.nvidia.com/labs/dvl/projects/native-segmentation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.16993>)

[PDF](<https://arxiv.org/pdf/2505.16993.pdf>)
