Character generation through self supervised vectorization

Gökçen, Gökçeoğlu
Humans learn visual concepts rapidly and flexibly from few samples. However, this kind of learning is a challenge for the prevalent machine learning methodologies. Currently, high performing deep learning models and algorithms depend on large amounts of data and they are task-specific. In this study, we focus on the generative aspects of visual concept learning in the domain of handwritten characters. We develop an unsupervised approach that can be generalized to multiple tasks using a small number of samples. We present a drawing agent that operates on stroke-level representation of images. At each time step, the agent first assesses the current canvas and decides whether to stop or keep drawing. When a `draw’ decision is made, the agent outputs a program indicating the stroke to be drawn. As a result, it produces a final raster image by drawing the strokes on a canvas, using a minimal number of strokes and dynamically deciding when to stop. We train our agent through reinforcement learning on handwritten character datasets for unconditional generation and parsing (reconstruction) tasks. We utilize our parsing agent for exemplar generation and type conditioned concept generation without any further training. We present successful results on all three generation tasks and the parsing task. Crucially, we do not need any stroke-level or vector supervision; we only use raster images for training.


Effect of human prior knowledge on game success and comparison with reinforcement learning
Hasanoğlu, Mert.; Çakır, Murat Perit; Department of Cognitive Sciences (2019)
This study aims to find out the effect of prior knowledge on the success of humans in a non-rewarding game environment, and then to compare human performance with a reinforcement learning method in an effort to observe to what extent this method can be brought closer to human behavior and performance with the data obtained. For this purpose, different versions of a simple 2D game were used, and data were collected from 32 participants. At the end of the experiment, it is concluded that prior knowledge, such...
Language learning from the perspective of nonlinear dynamic systems
Hohenberger, Annette Edeltraud; Peltzer-Karpf, Annemarie (Walter de Gruyter GmbH, 2009-01-01)
This article outlines a nonlinear dynamic systems approach to language learning on the basis of developmental cognitive neuroscience. Language learning, on this view, is a process of experience-dependent shaping and selection of broadly defined domain-general and domain-specific genetic predispositions. The central concept of development is (neuro) cognitive,e growth in terms of self-organization. Linguistic structure-building is synergetic and emergent insofar as the acquisition of a critical mass of eleme...
Cognitive analysis of experts' and novices' concept mapping processes
Doğusoy, Berrin; Çağıltay, Kürşat; Department of Computer Education and Instructional Technology (2012)
In this study, Concept map (CM) development processes of the experts and novices were explored. This studyaimed to investigate the similarities and differences among novices and experts’ CM development process regarding their cognitive processes. Two experiments were designed; eye-tracking, written and verbal data were collected from 29 pre-service teachers and 6 subject matter experts.Data were analyzed by using qualitative and quantitative data analysis methods. The results indicated that eventhough some ...
Competing labels: a heuristic approach to pseudo-labeling in deep semi-supervised learning
Bayrak, Hamdi Burak; Ertekin Bolelli, Şeyda; Yücel, Hamdullah; Department of Scientific Computing (2022-2-10)
Semi-supervised learning is one of the dominantly utilized approaches to reduce the reliance of deep learning models on large-scale labeled data. One mostly used method of this approach is pseudo-labeling. However, pseudo-labeling, especially its originally proposed form tends to remarkably suffer from noisy training when the assigned labels are false. In order to mitigate this problem, in our work, we investigate the gradient sent to the neural network and propose a heuristic method, called competing label...
Deep learning approach for laboratory mice grimace scaling
Eral, Mustafa; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2016)
Deep learning is extremely attractive research topic in pattern recognition and machine learning areas. Applications in speech recognition, natural language processing, and machine vision fields gained huge acceleration in performance by employing deep learning. In this thesis, deep learning is used for medical purposes in order to scale pain degree of drug stimulated mice by examining facial grimace. For this purpose each frame in the videos in the training set were scaled manually by experts according to ...
Citation Formats
G. Gökçen, “Character generation through self supervised vectorization,” M.S. - Master of Science, Middle East Technical University, 2022.