OBSER: Object-Based Sub-Environment Recognition for Zero-Shot Environmental Inference

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Choi, Won-Seok, Han, Dong-Sig, Choi, Suhyung, Yang, Hyeonseo, Zhang, Byoung-Tak
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913926104481792
author Choi, Won-Seok
Han, Dong-Sig
Choi, Suhyung
Yang, Hyeonseo
Zhang, Byoung-Tak
author_facet Choi, Won-Seok
Han, Dong-Sig
Choi, Suhyung
Yang, Hyeonseo
Zhang, Byoung-Tak
contents We present the Object-Based Sub-Environment Recognition (OBSER) framework, a novel Bayesian framework that infers three fundamental relationships between sub-environments and their constituent objects. In the OBSER framework, metric and self-supervised learning models estimate the object distributions of sub-environments on the latent space to compute these measures. Both theoretically and empirically, we validate the proposed framework by introducing the ($ε,δ$) statistically separable (EDS) function which indicates the alignment of the representation. Our framework reliably performs inference in open-world and photorealistic environments and outperforms scene-based methods in chained retrieval tasks. The OBSER framework enables zero-shot recognition of environments to achieve autonomous environment understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02929
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OBSER: Object-Based Sub-Environment Recognition for Zero-Shot Environmental Inference
Choi, Won-Seok
Han, Dong-Sig
Choi, Suhyung
Yang, Hyeonseo
Zhang, Byoung-Tak
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We present the Object-Based Sub-Environment Recognition (OBSER) framework, a novel Bayesian framework that infers three fundamental relationships between sub-environments and their constituent objects. In the OBSER framework, metric and self-supervised learning models estimate the object distributions of sub-environments on the latent space to compute these measures. Both theoretically and empirically, we validate the proposed framework by introducing the ($ε,δ$) statistically separable (EDS) function which indicates the alignment of the representation. Our framework reliably performs inference in open-world and photorealistic environments and outperforms scene-based methods in chained retrieval tasks. The OBSER framework enables zero-shot recognition of environments to achieve autonomous environment understanding.
title OBSER: Object-Based Sub-Environment Recognition for Zero-Shot Environmental Inference
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.02929