# SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding

Source: [SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding](<https://www.sota2.com/research/paper/68fa6d751e209131cea3a0f0>)

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

Data updated: 2025-10-28T13:56:55.331Z

Authors: Hermann Blum, Marcus G. M\\"uller, Abel Gawel, Roland Siegwart, Cesar Cadena

Published: 2022-06-21T18:41:51.000Z

## Abstract

In order to operate in human environments, a robot's semantic perception has to overcome open-world challenges such as novel objects and domain gaps. Autonomous deployment to such environments therefore requires robots to update their knowledge and learn without supervision. We investigate how a robot can autonomously discover novel semantic classes and improve accuracy on known classes when exploring an unknown environment. To this end, we develop a general framework for mapping and clustering that we then use to generate a self-supervised learning signal to update a semantic segmentation model. In particular, we show how clustering parameters can be optimized during deployment and that fusion of multiple observation modalities improves novel object discovery compared to prior work. Models, data, and implementations can be found at https://github.com/hermannsblum/scim

## 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/2206.10670>)

[PDF](<https://arxiv.org/pdf/2206.10670.pdf>)