Related papers: Data-Efficient Generation for Dataset Distillation

Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some…

This work presents Fair4Free, a novel generative model to generate synthetic fair data using data-free distillation in the latent space. Fair4Free can work on the situation when the data is private or inaccessible. In our approach, we first…

This technical report outlines our method for generating a synthetic dataset for semantic segmentation using a latent diffusion model. Our approach eliminates the need for additional models specifically trained on segmentation data and is…

Generative diffusion models have emerged as powerful tools to synthetically produce training data, offering potential solutions to data scarcity and reducing labelling costs for downstream supervised deep learning applications. However,…

Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. Current text…

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep inference procedure. To overcome this, diffusion distillation techniques produce student generators capable of matching or surpassing the teacher in…

Data Fairness is a crucial topic due to the recent wide usage of AI powered applications. Most of the real-world data is filled with human or machine biases and when those data are being used to train AI models, there is a chance that the…

Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively…

Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for…

Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not…

Diffusion models, such as Stable Diffusion (SD), offer the ability to generate high-resolution images with diverse features, but they come at a significant computational and memory cost. In classifier-free guided diffusion models, prolonged…

In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets. To…

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing computational demands of modern deep learning. Recently,…

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 datasets that are relevant for a downstream task. We propose…

Deep learning models often require large amounts of data for training, leading to increased costs. It is particularly challenging in medical imaging, i.e., gathering distributed data for centralized training, and meanwhile, obtaining…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…