# DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation

Source: [DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation](<https://www.sota2.com/research/paper/68fa79f81e209131cea805bf>)

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

Data updated: 2025-10-26T05:09:30.174Z

Authors: Ivan Martinovi\\'c, Josip \\v{S}ari\\'c, Marin Or\\v{s}i\\'c, Matej Kristan, Sini\\v{s}a \\v{S}egvi\\'c

Published: 2025-07-14T10:01:02.000Z

## Abstract

Pixel-level annotation is expensive and time-consuming. Semi-supervised segmentation methods address this challenge by learning models on few labeled images alongside a large corpus of unlabeled images. Although foundation models could further account for label scarcity, effective mechanisms for their exploitation remain underexplored. We address this by devising a novel semi-supervised panoptic approach fueled by two dedicated foundation models. We enhance recognition by complementing unsupervised mask-transformer consistency with zero-shot classification of CLIP features. We enhance localization by class-agnostic decoder warm-up with respect to SAM pseudo-labels. The resulting decoupled enhancement of recognition and localization (DEARLi) particularly excels in the most challenging semi-supervised scenarios with large taxonomies and limited labeled data. Moreover, DEARLi outperforms the state of the art in semi-supervised semantic segmentation by a large margin while requiring 8x less GPU memory, in spite of being trained only for the panoptic objective. We observe 29.9 PQ and 38.9 mIoU on ADE20K with only 158 labeled images. The source code is available at https://github.com/helen1c/DEARLi.

## 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/2507.10118>)

[PDF](<https://arxiv.org/pdf/2507.10118.pdf>)