Related papers: Diversifying Sample Generation for Accurate Data-F…

Post-training quantization is a representative technique for compressing neural networks, making them smaller and more efficient for deployment on edge devices. However, an inaccessible user dataset often makes it difficult to ensure the…

In distributed training, the communication cost due to the transmission of gradients or the parameters of the deep model is a major bottleneck in scaling up the number of processing nodes. To address this issue, we propose \emph{dithered…

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…

The importance of Synthetic Data Generation (SDG) has increased significantly in domains where data quality is poor or access is limited due to privacy and regulatory constraints. One such domain is recruitment, where publicly available…

Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that…

Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies…

Data-hunger and data-imbalance are two major pitfalls in many deep learning approaches. For example, on highly optimized production lines, defective samples are hardly acquired while non-defective samples come almost for free. The defects…

Domain generalization (DG) is a prevalent problem in real-world applications, which aims to train well-generalized models for unseen target domains by utilizing several source domains. Since domain labels, i.e., which domain each data point…

Mixed-precision quantization has been widely applied on deep neural networks (DNNs) as it leads to significantly better efficiency-accuracy tradeoffs compared to uniform quantization. Meanwhile, determining the exact precision of each layer…

In order to achieve good performance and generalisability, medical image segmentation models should be trained on sizeable datasets with sufficient variability. Due to ethics and governance restrictions, and the costs associated with…

Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…

Large Language Models (LLMs) such as GPT-4 and Llama3 have significantly impacted various fields by enabling high-quality synthetic data generation and reducing dependence on expensive human-generated datasets. Despite this, challenges…

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

In Self-Supervised Learning (SSL), models are typically pretrained, fine-tuned, and evaluated on the same domains. However, they tend to perform poorly when evaluated on unseen domains, a challenge that Unsupervised Domain Generalization…

This paper addresses the challenge of incremental learning in growing graphs with increasingly complex tasks. The goal is to continuously train a graph model to handle new tasks while retaining proficiency in previous tasks via memory…

The instability in GAN training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing feature matching with mini-batch statistics, due to a fragile…

Knowledge distillation (KD) has enabled remarkable progress in model compression and knowledge transfer. However, KD requires a large volume of original data or their representation statistics that are not usually available in practice.…

Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data collection.…