相关论文: Opt-In Art: Learning Art Styles Only from Few Exam…

The ability to learn from a small number of examples has been a difficult problem in machine learning since its inception. While methods have succeeded with large amounts of training data, research has been underway in how to accomplish…

In this paper, we are interested in the few-shot learning problem. In particular, we focus on a challenging scenario where the number of categories is large and the number of examples per novel category is very limited, e.g. 1, 2, or 3.…

We present an approach to example-based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real-time semantically…

When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as…

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pretraining on…

Arbitrary Style Transfer is a technique used to produce a new image from two images: a content image, and a style image. The newly produced image is unseen and is generated from the algorithm itself. Balancing the structure and style…

The advent of artificial intelligence has contributed in a groundbreaking transformation of the fashion industry, redefining creativity and innovation in unprecedented ways. This work investigates methodologies for generating tailored…

Image datasets are commonly used in psychophysical experiments and in machine learning research. Most publicly available datasets are comprised of images of realistic and natural objects. However, while typical machine learning models lack…

Recent advances in text-to-image generative models provide the ability to generate high-quality images from short text descriptions. These foundation models, when pre-trained on billion-scale datasets, are effective for various downstream…

Given a finite and noisy dataset generated with a closed-form mathematical model, when is it possible to learn the true generating model from the data alone? This is the question we investigate here. We show that this model-learning problem…

We present a novel, regression-based method for artistically styling images. Unlike recent neural style transfer or diffusion-based approaches, our method allows for explicit control over the stroke composition and level of detail in the…

Painting is one of the ways for people to express their ideas, but what if people with disabilities in hands want to paint? To tackle this challenge, we create an end-to-end solution that can generate artistic images from text descriptions.…

Synthetic image source attribution is a challenging task, especially in data scarcity conditions requiring few-shot or zero-shot classification capabilities. We present a new training-free one-shot attribution method based on image…

With the advancement of neural generative capabilities, the art community has increasingly embraced GenAI (Generative Artificial Intelligence), particularly large text-to-image models, for producing aesthetically compelling results.…

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

Consider the following problem: given a few demonstrations of a task across a few different objects, how can a robot learn to perform that same task on new, previously unseen objects? This is challenging because the large variety of objects…

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in…

Recent powerful vision classifiers are biased towards textures, while shape information is overlooked by the models. A simple attempt by augmenting training images using the artistic style transfer method, called Stylized ImageNet, can…

Language-guided image editing has achieved great success recently. In this paper, for the first time, we investigate exemplar-guided image editing for more precise control. We achieve this goal by leveraging self-supervised training to…

Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language and out-of-distribution effects make it hard to synthesize image styles, that…