Jigsaw: the unsupervised construction of spatial representations
نویسندگان
چکیده
A fundamental assumption in machine vision is that the spatial arrangement of pixels is given. In challenging this assumption we have utilised a general relationship that exists between space and behaviour. This relationship presents itself as spatial redundancy, which other researchers have considered problematic. We present a mathematical model and empirical investigations into this relationship and develop an algorithm, JIGSAW, which uses it to build spatial representations. The philosophy underpinning JIGSAW takes signal behaviour, rather than position, as primary. JIGSAW is an unsupervised learning algorithm that is efficient in time and space and that makes minimal assumptions about its operating domain. This algorithm offers engineering potential, opportunities in the understanding of biological vision, and a contribution to the wider field of cognitive science.
منابع مشابه
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
In this paper we study the problem of image representation learning without human annotation. Following the principles of selfsupervision, we build a convolutional neural network (CNN) that can be trained to solve Jigsaw puzzles as a pretext task, which requires no manual labeling, and then later repurposed to solve object classification and detection. To maintain the compatibility across tasks...
متن کاملSaliency Cognition of Urban Monuments Based on Verbal Descriptions of Mental-Spatial Representations (Case Study: Urban Monuments in Qazvin)
Urban monuments encompass a wide range of architectural works either intentionally or unintentionally. These works are often salient due to their inherently explicit or hidden components and qualities in the urban context. Therefore, they affect the mental-spatial representations of the environment and make the city legible. However, the ambiguity of effective components often complicates their...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملDeveloping a BIM-based Spatial Ontology for Semantic Querying of 3D Property Information
With the growing dominance of complex and multi-level urban structures, current cadastral systems, which are often developed based on 2D representations, are not capable of providing unambiguous spatial information about urban properties. Therefore, the concept of 3D cadastre is proposed to support 3D digital representation of land and properties and facilitate the communication of legal owners...
متن کاملVirtual 3D Jigsaw Puzzles: Studying the Effect of Exploring Spatial Relations with Implicit Guidance
This paper investigates the engaging concept of virtual 3D jigsaw puzzles to foster the understanding of spatial relations within technical or biological systems by means of virtual models. Employing an application in anatomy education, it answers the question: How does guided spatial exploration, arising while composing a 3D jigsaw, affect the acquisition of spatial-functional understanding in...
متن کامل