Related papers: Learning from Synthetic Data via Provenance-Based …

Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work…

Generative models have the ability to synthesize data points drawn from the data distribution, however, not all generated samples are high quality. In this paper, we propose using a combination of coresets selection methods and ``entropic…

Most approaches to dense anomaly detection rely on generative modeling or on discriminative methods that train with negative data. We consider a recent hybrid method that optimizes the same shared representation according to cross-entropy…

The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…

Self-supervised learning, a.k.a., pretraining, is important in natural language processing. Most of the pretraining methods first randomly mask some positions in a sentence and then train a model to recover the tokens at the masked…

Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understood. We formalize synthetic augmentation as a modification of the effective training…

Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the training of generative adversarial networks (GANs) is an…

Individual-level data (microdata) that characterizes a population, is essential for studying many real-world problems. However, acquiring such data is not straightforward due to cost and privacy constraints, and access is often limited to…

Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions. Still, the usability of existing methods is limited to image classification models. To overcome this…

Unsupervised representation learning has been extensively employed in anomaly detection, achieving impressive performance. Extracting valuable feature vectors that can remarkably improve the performance of anomaly detection are essential in…

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel…

Model-free deep reinforcement learning (RL) agents can learn an effective policy directly from repeated interactions with a black-box environment. However in practice, the algorithms often require large amounts of training experience to…

Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity for a computer to learn from data accurately and efficiently…

We address the challenging problem of deep representation learning--the efficient adaption of a pre-trained deep network to different tasks. Specifically, we propose to explore gradient-based features. These features are gradients of the…

Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies…

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the expense of generation diversity, limiting the utility of these…

Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, policies trained on offline data often struggle to generalise…