相关论文: DUSE: A Data Expansion Framework for Low-resource …

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…

Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such…

Automated data augmentation, which aims at engineering augmentation policy automatically, recently draw a growing research interest. Many previous auto-augmentation methods utilized a Density Matching strategy by evaluating policies in…

Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically…

With the continuous advancement of processors, modern micro-architecture designs have become increasingly complex. The vast design space presents significant challenges for human designers, making design space exploration (DSE) algorithms a…

Automatic modulation recognition (AMR) is a promising technology for intelligent communication receivers to detect signal modulation schemes. Recently, the emerging deep learning (DL) research has facilitated high-performance DL-AMR…

Multimodal learning has demonstrated incredible successes by integrating diverse data sources, yet it often relies on the availability of all modalities - an assumption that rarely holds in real-world applications. Pretrained multimodal…

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways…

Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference. Dynamic sparse training (DST), as a leading sparse training approach, can…

In this paper, we present Morse, a simple dual-sampling framework for accelerating diffusion models losslessly. The key insight of Morse is to reformulate the iterative generation (from noise to data) process via taking advantage of fast…

Class imbalance is a challenging issue in practical classification problems for deep learning models as well as traditional models. Traditionally successful countermeasures such as synthetic over-sampling have had limited success with…

Deep transfer learning techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge. However, the current DTL techniques suffer from either…

Unsupervised person search aims to localize a particular target person from a gallery set of scene images without annotations, which is extremely challenging due to the unexpected variations of the unlabeled domains. However, most existing…

The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available processing power. While recent research has made significant strides in developing pruning…

As Retrieval-Augmented Generation (RAG) systems evolve toward more sophisticated architectures, ensuring their trustworthiness through explainable and robust evaluation becomes critical. Existing scalar metrics suffer from limited…

Data imbalance is ubiquitous when applying machine learning to real-world problems, particularly regression problems. If training data are imbalanced, the learning is dominated by the densely covered regions of the target distribution and…

Deep learning has been shown to be highly effective for automatic modulation classification (AMC), which is a pivotal technology for next-generation cognitive communications. Yet, existing deep learning methods for AMC often lack robust…

Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However,…

The scarcity and complexity of voxel-level annotations in 3D medical imaging present significant challenges, particularly due to the domain gap between labeled datasets from well-resourced centers and unlabeled datasets from less-resourced…

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware…