PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cavagnero, Niccolò, Norouzi, Narges, Dubbelman, Gijs, de Geus, Daan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917363031474176
author Cavagnero, Niccolò
Norouzi, Narges
Dubbelman, Gijs
de Geus, Daan
author_facet Cavagnero, Niccolò
Norouzi, Narges
Dubbelman, Gijs
de Geus, Daan
contents Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-based encoder-only models for image and video segmentation, such as EoMT and VidEoMT, achieve competitive accuracy with remarkably low latency, yet they require finetuning the encoder, sacrificing the multi-task encoder sharing that makes VFMs practically attractive for large-scale deployment. To reconcile encoder-only simplicity and speed with frozen VFM features, we propose the Plain Mask Decoder (PMD), a fast Transformer-based segmentation decoder that operates on top of frozen VFM features. The resulting model, the Plain Mask Transformer (PMT), preserves the architectural simplicity and low latency of encoder-only designs while keeping the encoder representation unchanged and shareable. The design seamlessly applies to both image and video segmentation, inheriting the generality of the encoder-only framework. On standard image segmentation benchmarks, PMT matches the frozen-encoder state of the art while running up to ~3x faster. For video segmentation, it even performs on par with fully finetuned methods, while being up to 8x faster than state-of-the-art frozen-encoder models. Code: https://github.com/tue-mps/pmt.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25398
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders
Cavagnero, Niccolò
Norouzi, Narges
Dubbelman, Gijs
de Geus, Daan
Computer Vision and Pattern Recognition
Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-based encoder-only models for image and video segmentation, such as EoMT and VidEoMT, achieve competitive accuracy with remarkably low latency, yet they require finetuning the encoder, sacrificing the multi-task encoder sharing that makes VFMs practically attractive for large-scale deployment. To reconcile encoder-only simplicity and speed with frozen VFM features, we propose the Plain Mask Decoder (PMD), a fast Transformer-based segmentation decoder that operates on top of frozen VFM features. The resulting model, the Plain Mask Transformer (PMT), preserves the architectural simplicity and low latency of encoder-only designs while keeping the encoder representation unchanged and shareable. The design seamlessly applies to both image and video segmentation, inheriting the generality of the encoder-only framework. On standard image segmentation benchmarks, PMT matches the frozen-encoder state of the art while running up to ~3x faster. For video segmentation, it even performs on par with fully finetuned methods, while being up to 8x faster than state-of-the-art frozen-encoder models. Code: https://github.com/tue-mps/pmt.
title PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.25398