相关论文: When, Why, and Which Pretrained GANs Are Useful?

Active Appearance Models (AAMs) are a well-established technique for fitting deformable models to images, but they are limited by linear appearance assumptions and can struggle with complex variations. In this paper, we explore if the AAM…

Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labeled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and…

StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad…

GANs provide a framework for training generative models which mimic a data distribution. However, in many cases we wish to train these generative models to optimize some auxiliary objective function within the data it generates, such as…

The goal of filter pruning is to search for unimportant filters to remove in order to make convolutional neural networks (CNNs) efficient without sacrificing the performance in the process. The challenge lies in finding information that can…

Fairness has become an essential problem in many domains of Machine Learning (ML), such as classification, natural language processing, and Generative Adversarial Networks (GANs). In this research effort, we study the unfairness of GANs. We…

1. Research question: With the growing interest in skin diseases and skin aesthetics, the ability to predict facial wrinkles is becoming increasingly important. This study aims to evaluate whether a computational model, convolutional neural…

Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application…

Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation error, the fundamental limitation of the network in…

Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to minimise demographic bias in AI, this problem remains…

Anyone can take a photo, but not everybody has the ability to retouch their pictures and obtain result close to professional. Since it is not possible to ask experts to retouch thousands of pictures, we thought about teaching a piece of…

Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

The tremendous success of ImageNet-trained deep features on a wide range of transfer tasks begs the question: what are the properties of the ImageNet dataset that are critical for learning good, general-purpose features? This work provides…

In recent years, pretrained models revolutionized the paradigm of natural language understanding (NLU), where we append a randomly initialized classification head after the pretrained backbone, e.g. BERT, and finetune the whole model. As…

Generative Adversarial Networks (GANs) have high computational costs to train their complex architectures. Throughout the training process, GANs' output is analyzed qualitatively based on the loss and synthetic images' diversity and…

In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination…

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over…

Despite the recent success of GANs in synthesizing images conditioned on inputs such as a user sketch, text, or semantic labels, manipulating the high-level attributes of an existing natural photograph with GANs is challenging for two…

One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage previously acquired knowledge to converge faster on the current task. Usually this is done through fine-tuning, where an implicit…