相关论文: DiRe: Diversity-promoting Regularization for Datas…

Dataset distillation synthesizes a small set of images from a large-scale real dataset such that synthetic and real images share similar behavioral properties (e.g, distributions of gradients or features) during a training process. Through…

Modern machine learning models heavily rely on large datasets that often include sensitive and private information, raising serious privacy concerns. Differentially private (DP) data generation offers a solution by creating synthetic…

We review some recent work on removing hidden confounding and causal regularization from a unified viewpoint. We describe how simple and user-friendly techniques improve stability, replicability and distributional robustness in…

Dataset Distillation (DD) is a promising technique to synthesize a smaller dataset that preserves essential information from the original dataset. This synthetic dataset can serve as a substitute for the original large-scale one, and help…

The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset. Until now, no method of Dataset…

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods…

Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that…

What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has shown can be used to compress large datasets into a small set of…

Dataset distillation is attracting more attention in machine learning as training sets continue to grow and the cost of training state-of-the-art models becomes increasingly high. By synthesizing datasets with high information density,…

Dataset Distillation (DD) compresses large datasets into compact synthetic ones that maintain training performance. However, current methods mainly target sample reduction, with limited consideration of data precision and its impact on…

Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical.…

In open-domain Question Answering (QA), dense retrieval is crucial for finding relevant passages for answer generation. Typically, contrastive learning is used to train a retrieval model that maps passages and queries to the same semantic…

Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based methods have attracted attention for their high efficiency.…

Diversity control is an important task to alleviate bias amplification and filter bubble problems. The desired degree of diversity may fluctuate based on users' daily moods or business strategies. However, existing methods for controlling…

Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel…

Multimodal Dataset Distillation (MDD) seeks to condense large-scale image-text datasets into compact surrogates while retaining their effectiveness for cross-modal learning. Despite recent progress, existing MDD approaches often suffer from…

It is essential but challenging to share medical image datasets due to privacy issues, which prohibit building foundation models and knowledge transfer. In this paper, we propose a novel dataset distillation method to condense the original…

Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields. However, training such models requires huge amounts of data, increasing the computational time and cost. To address this, dataset…

Dataset condensation (DC) enables the creation of compact, privacy-preserving synthetic datasets that can match the utility of real patient records, supporting democratised access to highly regulated clinical data for developing downstream…

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…