A review on generative adversarial networks: Algorithms, theory, and applications
Generative adversarial networks (GANs) have recently become a hot research topic;
however, they have been studied since 2014, and a large number of algorithms have been …
however, they have been studied since 2014, and a large number of algorithms have been …
Deep reinforcement learning in computer vision: a comprehensive survey
Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …
the powerful representation of deep neural networks. Recent works have demonstrated the …
Coderl: Mastering code generation through pretrained models and deep reinforcement learning
Program synthesis or code generation aims to generate a program that satisfies a problem
specification. Recent approaches using large-scale pretrained language models (LMs) have …
specification. Recent approaches using large-scale pretrained language models (LMs) have …
Clipasso: Semantically-aware object sketching
Abstraction is at the heart of sketching due to the simple and minimal nature of line
drawings. Abstraction entails identifying the essential visual properties of an object or scene …
drawings. Abstraction entails identifying the essential visual properties of an object or scene …
[图书][B] Synthetic data for deep learning
SI Nikolenko - 2021 - Springer
You are holding in your hands… oh, come on, who holds books like this in their hands
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
Dreamcoder: Bootstrapping inductive program synthesis with wake-sleep library learning
We present a system for inductive program synthesis called DreamCoder, which inputs a
corpus of synthesis problems each specified by one or a few examples, and automatically …
corpus of synthesis problems each specified by one or a few examples, and automatically …
Differentiable vector graphics rasterization for editing and learning
We introduce a differentiable rasterizer that bridges the vector graphics and raster image
domains, enabling powerful raster-based loss functions, optimization procedures, and …
domains, enabling powerful raster-based loss functions, optimization procedures, and …
Abstraction and analogy‐making in artificial intelligence
M Mitchell - Annals of the New York Academy of Sciences, 2021 - Wiley Online Library
Conceptual abstraction and analogy‐making are key abilities underlying humans' abilities to
learn, reason, and robustly adapt their knowledge to new domains. Despite a long history of …
learn, reason, and robustly adapt their knowledge to new domains. Despite a long history of …
Learning to generate line drawings that convey geometry and semantics
This paper presents an unpaired method for creating line drawings from photographs.
Current methods often rely on high quality paired datasets to generate line drawings …
Current methods often rely on high quality paired datasets to generate line drawings …
Meta-sim: Learning to generate synthetic datasets
Training models to high-end performance requires availability of large labeled datasets,
which are expensive to get. The goal of our work is to automatically synthesize labeled …
which are expensive to get. The goal of our work is to automatically synthesize labeled …