# S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision

Source: [S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision](<https://www.sota2.com/research/paper/68fa7a921e209131cea83f81>)

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

Data updated: 2025-10-26T05:22:59.712Z

Authors: Huihui Xu, Jin Ye, Hongqiu Wang, Changkai Ji, Jiashi Lin, Ming Hu, Ziyan Huang, Ying Chen, Chenglong Ma, Tianbin Li, Lihao Liu, Junjun He, Lei Zhu

Published: 2025-08-09T14:12:39.000Z

## Abstract

Recent self-supervised image segmentation models have achieved promising performance on semantic segmentation and class-agnostic instance segmentation. However, their pretraining schedule is multi-stage, requiring a time-consuming pseudo-masks generation process between each training epoch. This time-consuming offline process not only makes it difficult to scale with training dataset size, but also leads to sub-optimal solutions due to its discontinuous optimization routine. To solve these, we first present a novel pseudo-mask algorithm, Fast Universal Agglomerative Pooling (UniAP). Each layer of UniAP can identify groups of similar nodes in parallel, allowing to generate both semantic-level and instance-level and multi-granular pseudo-masks within ens of milliseconds for one image. Based on the fast UniAP, we propose the Scalable Self-Supervised Universal Segmentation (S2-UniSeg), which employs a student and a momentum teacher for continuous pretraining. A novel segmentation-oriented pretext task, Query-wise Self-Distillation (QuerySD), is proposed to pretrain S2-UniSeg to learn the local-to-global correspondences. Under the same setting, S2-UniSeg outperforms the SOTA UnSAM model, achieving notable improvements of AP+6.9 on COCO, AR+11.1 on UVO, PixelAcc+4.5 on COCOStuff-27, RQ+8.0 on Cityscapes. After scaling up to a larger 2M-image subset of SA-1B, S2-UniSeg further achieves performance gains on all four benchmarks. Our code and pretrained models are available at https://github.com/bio-mlhui/S2-UniSeg

## 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/2508.06995>)

[PDF](<https://arxiv.org/pdf/2508.06995.pdf>)
