Unsupervised Place Discovery for Place-Specific Change Classifier

نویسندگان

  • Xiaoxiao Fei
  • Kanji Tanaka
چکیده

In this study, we address the problem of supervised change detection for robotic map learning applications, in which the aim is to train a place-specific change classifier (e.g., support vector machine (SVM)) to predict changes from a robot's view image. An open question is the manner in which to partition a robot's workspace into places (e.g., SVMs) to maximize the overall performance of change classifiers. This is a chicken-or-egg problem: if we have a well-trained change classifier, partitioning the robot's workspace into places is rather easy. However, training a change classifier requires a set of place-specific training data. In this study, we address this novel problem, which we term unsupervised place discovery. In addition, we present a solution powered by convolutional-feature-based visual place recognition, and validate our approach by applying it to two place-specific change classifiers, namely, nuisance and anomaly predictors.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Zero-Shot Learning to Manage a Large Number of Place-Specific Compressive Change Classifiers

With recent progress in large-scale map maintenance and long-term map learning, the task of change detection on a large-scale map from a visual image captured by a mobile robot has become a problem of increasing criticality. Previous approaches for change detection are typically based on image differencing and require the memorization of a prohibitively large number of mapped images in the abov...

متن کامل

Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016

We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking problem as pairwise classification and utilizes an unsupervised neural feature ensemble approach to learn latent features of users. Combined with traditional ha...

متن کامل

Sensitivity change of dopamine receptors in hippocampus (CA1) and its effect on morphine-induced condition place preference

In the present study, the effects of intra-cerebral hippocampus (CA1) injections of apomorphine D1, D2-like receptors agonists on morphine-induced place preference in male Wistar rats have been investigated. Subcutaneous administration of different dose of morphine sulphate (1, 3, 6 and 9 mg/kg) produced a dose-dependent conditioned place preference (CPP). Intra-cerebral hippocampus (CA1) admin...

متن کامل

Sensitivity change of dopamine receptors in hippocampus (CA1) and its effect on morphine-induced condition place preference

In the present study, the effects of intra-cerebral hippocampus (CA1) injections of apomorphine D1, D2-like receptors agonists on morphine-induced place preference in male Wistar rats have been investigated. Subcutaneous administration of different dose of morphine sulphate (1, 3, 6 and 9 mg/kg) produced a dose-dependent conditioned place preference (CPP). Intra-cerebral hippocampus (CA1) admin...

متن کامل

The Place-Name as an Intangible Place of Memory (A Holistic Approach in Reading the Place-Names through a Comparative-Analytical Study on the Character of Name and Place)

Understanding architectural heritage and their various aspects have always been a subject of focus for the international conservation communities. Within the recent decades, eventhough the place-names are part of the living history as well as cultural heritage, they have still constantly been facing quick precipitant changes. As such, in the Conservation literature, most studies have skipped ad...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1706.02054  شماره 

صفحات  -

تاریخ انتشار 2017