Related papers: Continual Personalization for Diffusion Models

In this paper, we present a novel use of an anisotropic diffusion model for automatic detection of neurons in histological sections of the adult human brain cortex. We use a partial differential equation model to process high resolution…

Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization using specific images. These methods enable generating images of…

We introduce a new general-purpose approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in…

Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising…

The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the…

Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural…

Noise injection is a fundamental tool for data augmentation, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying different noise models of varying…

Conventional intelligent systems based on deep neural network (DNN) models encounter challenges in achieving human-like continual learning due to catastrophic forgetting. Here, we propose a metaplasticity model inspired by human working…

Benefiting from the significant advancements in text-to-image diffusion models, research in personalized image generation, particularly customized portrait generation, has also made great strides recently. However, existing methods either…

Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from severe artifacts under sparse-view settings. To address this, we propose DiffNR, a novel…

Accelerating deep neural network (DNN) inference on resource-limited devices is one of the most important barriers to ensuring a wider and more inclusive adoption. To alleviate this, DNN binary quantization for faster convolution and memory…

Recent work has demonstrated a remarkable ability to customize text-to-image diffusion models to multiple, fine-grained concepts in a sequential (i.e., continual) manner while only providing a few example images for each concept. This…

Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. We argue that the denoising process is crucially limited by an accumulation of the…

Purpose: Magnetic Resonance Imaging (MRI) enables non-invasive assessment of brain abnormalities during early life development. Permanent magnet scanners operating in the neonatal intensive care unit (NICU) facilitate MRI of sick infants,…

Recent text-to-image customization works have proven successful in generating images of given concepts by fine-tuning diffusion models on a few examples. However, tuning-based methods inherently tend to overfit the concepts, resulting in…

Person search aims to jointly perform person detection and re-identification by localizing and identifying a query person within a gallery of uncropped scene images. Existing methods predominantly utilize ImageNet pre-trained backbones,…

Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model…

While many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we propose a method…

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning…

Despite continued advancement in recent years, deep neural networks still rely on large amounts of training data to avoid overfitting. However, labeled training data for real-world applications such as healthcare is limited and difficult to…