Abstracting Sketches Through Simple Primitives
نویسندگان
چکیده
Humans show high-level of abstraction capabilities in games that require quickly communicating object information. They decompose the message content into multiple parts and communicate them an interpretable protocol. Toward equipping machines with such capabilities, we propose Primitive-based Sketch Abstraction task where goal is to represent sketches using a fixed set drawing primitives under influence budget. To solve this task, our Primitive-Matching Network (PMN), learns abstractions sketch self supervised manner. Specifically, PMN maps each stroke its most similar primitive given set, predicting affine transformation aligns selected target stroke. We learn stroke-to-primitive mapping end-to-end distance-transform loss minimal when original precisely reconstructed predicted primitives. Our empirically achieves highest performance on recognition sketch-based image retrieval communication budget, while at same time being highly interpretable. This opens up new possibilities for analysis, as comparing by extracting relevant define category. Code available https://github.com/ExplainableML/sketch-primitives .
منابع مشابه
Abstracting Complex Languages through Transformation and Composition
ing Complex Languages through Transformation and Composition Jendrik Johannes, Steffen Zschaler, Miguel A. Fernández, Antonio Castillo, Dimitrios S. Kolovos, and Richard F. Paige 1 Technische Universität Dresden, [email protected] 2 Computing Department, Lancaster University, [email protected] 3 Telefónica Research & Development, [email protected],[email protected] 4 Department of Compu...
متن کاملMotor learning through the combination of primitives.
In this paper we discuss a new perspective on how the central nervous system (CNS) represents and solves some of the most fundamental computational problems of motor control. In particular, we consider the task of transforming a planned limb movement into an adequate set of motor commands. To carry out this task the CNS must solve a complex inverse dynamic problem. This problem involves the tra...
متن کاملDeriving Motor Primitives Through Action Segmentation
The purpose of the present experiment is to further understand the effect of levels of processing (top-down vs. bottom-up) on the perception of movement kinematics and primitives for grasping actions in order to gain insight into possible primitives used by the mirror system. In the present study, we investigated the potential of identifying such primitives using an action segmentation task. Sp...
متن کاملAction recognition and understanding through motor primitives
In robotics, recognition of human activity has been used extensively for robot task learning through imitation and demonstration. However, there has not been much work on modeling and recognition of activities that involve object manipulation and grasping. In this work, we deal with single arm/hand actions which are very similar to each other in terms of arm/hand motions. The approach is based ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Lecture Notes in Computer Science
سال: 2022
ISSN: ['1611-3349', '0302-9743']
DOI: https://doi.org/10.1007/978-3-031-19818-2_23