Saved in:
Bibliographic Details
Main Authors: Takeda, Koji, Tanaka, Kanji, Nakamura, Yoshimasa, Kanezaki, Asako
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.06185
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917662654726144
author Takeda, Koji
Tanaka, Kanji
Nakamura, Yoshimasa
Kanezaki, Asako
author_facet Takeda, Koji
Tanaka, Kanji
Nakamura, Yoshimasa
Kanezaki, Asako
contents In everyday indoor navigation, robots often needto detect non-distinctive small-change objects (e.g., stationery,lost items, and junk, etc.) to maintain domain knowledge. Thisis most relevant to ground-view change detection (GVCD), a recently emerging research area in the field of computer vision.However, these existing techniques rely on high-quality class-specific object priors to regularize a change detector modelthat cannot be applied to semantically nondistinctive smallobjects. To address ill-posedness, in this study, we explorethe concept of degree-of-ill-posedness (DoI) from the newperspective of GVCD, aiming to improve both passive and activevision. This novel DoI problem is highly domain-dependent,and manually collecting fine-grained annotated training datais expensive. To regularize this problem, we apply the conceptof self-supervised learning to achieve efficient DoI estimationscheme and investigate its generalization to diverse datasets.Specifically, we tackle the challenging issue of obtaining self-supervision cues for semantically non-distinctive unseen smallobjects and show that novel "oversegmentation cues" from openvocabulary semantic segmentation can be effectively exploited.When applied to diverse real datasets, the proposed DoI modelcan boost state-of-the-art change detection models, and it showsstable and consistent improvements when evaluated on real-world datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06185
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection
Takeda, Koji
Tanaka, Kanji
Nakamura, Yoshimasa
Kanezaki, Asako
Computer Vision and Pattern Recognition
In everyday indoor navigation, robots often needto detect non-distinctive small-change objects (e.g., stationery,lost items, and junk, etc.) to maintain domain knowledge. Thisis most relevant to ground-view change detection (GVCD), a recently emerging research area in the field of computer vision.However, these existing techniques rely on high-quality class-specific object priors to regularize a change detector modelthat cannot be applied to semantically nondistinctive smallobjects. To address ill-posedness, in this study, we explorethe concept of degree-of-ill-posedness (DoI) from the newperspective of GVCD, aiming to improve both passive and activevision. This novel DoI problem is highly domain-dependent,and manually collecting fine-grained annotated training datais expensive. To regularize this problem, we apply the conceptof self-supervised learning to achieve efficient DoI estimationscheme and investigate its generalization to diverse datasets.Specifically, we tackle the challenging issue of obtaining self-supervision cues for semantically non-distinctive unseen smallobjects and show that novel "oversegmentation cues" from openvocabulary semantic segmentation can be effectively exploited.When applied to diverse real datasets, the proposed DoI modelcan boost state-of-the-art change detection models, and it showsstable and consistent improvements when evaluated on real-world datasets.
title Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.06185