相关论文: Diffusion-based Data Augmentation and Knowledge Di…

Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models has…

Dataset Distillation (DD) synthesizes a compact synthetic dataset that preserves the training utility of a full dataset. However, its standard formulation assumes that test data follow the same distribution as training data, an assumption…

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…

An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to…

Despite recent advances in dexterous manipulations, the manipulation of articulated objects and generalization across different categories remain significant challenges. To address these issues, we introduce DART, a novel framework that…

Despite pre-trained language models such as BERT have achieved appealing performance in a wide range of natural language processing tasks, they are computationally expensive to be deployed in real-time applications. A typical method is to…

Safe artificial intelligence for perception tasks remains a major challenge, partly due to the lack of data with high-quality labels. Annotations themselves are subject to aleatoric and epistemic uncertainty, which is typically ignored…

Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices. Data-free distillation provides an alternative for…

Deep neural networks trained with Empirical Risk Minimization (ERM) perform well when both training and test data come from the same domain, but they often fail to generalize to out-of-distribution samples. In image classification, these…

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…

Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire…

We study the problem of dataset distillation - creating a small set of synthetic examples capable of training a good model. In particular, we study the problem of label distillation - creating synthetic labels for a small set of real…

Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To…

Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model. However, it still suffers from highdemand in time and computational resources caused by sequential train-ing pipeline. Furthermore, the soft…

Generative models have recently undergone significant advancement due to the diffusion models. The success of these models can be often attributed to their use of guidance techniques, such as classifier or classifier-free guidance, which…

Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. In this paper, we…

The introduction of new generation hyperspectral satellite sensors, combined with advancements in deep learning methodologies, has significantly enhanced the ability to discriminate detailed land-cover classes at medium-large scales.…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

Collecting pixel-level labels for medical datasets can be a laborious and expensive process, and enhancing segmentation performance with a scarcity of labeled data is a crucial challenge. This work introduces AugPaint, a data augmentation…

Road crack segmentation is critical for robotic systems tasked with the inspection, maintenance, and monitoring of road infrastructures. Existing deep learning-based methods for crack segmentation are typically trained on specific datasets,…