Related papers: Feature Quantization Improves GAN Training

We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets and reach extreme compression levels below 8-bit precision. Unlike standard quantization-aware training (QAT)…

Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the…

Neural network quantization is widely used to reduce model inference complexity in real-world deployments. However, traditional integer quantization suffers from accuracy degradation when adapting to various dynamic ranges. Recent research…

Facial attribute editing aims to modify target attributes while preserving attribute-irrelevant content and overall image fidelity. Existing GAN-based methods provide favorable controllability, but often suffer from weak alignment between…

Detectors often suffer from performance drop due to domain gap between training and testing data. Recent methods explore diffusion models applied to domain generalization (DG) and adaptation (DA) tasks, but still struggle with large…

Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…

Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model…

Lack of annotated samples greatly restrains the direct application of deep learning in remote sensing image scene classification. Although researches have been done to tackle this issue by data augmentation with various image transformation…

Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN…

Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality training data while producing a small number (e.g., tens) of…

Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world scenarios, distributions may differ significantly…

Recently, video diffusion models (VDMs) have garnered significant attention due to their notable advancements in generating coherent and realistic video content. However, processing multiple frame features concurrently, coupled with the…

Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a…

Generative Adversarial Networks (GANs) have made significant progress in enhancing the quality of image synthesis. Recent methods frequently leverage pretrained networks to calculate perceptual losses or utilize pretrained feature spaces.…

Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the…

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sample. This is because the task of evaluating the quality of…

Medical image classification is one of the most critical problems in the image recognition area. One of the major challenges in this field is the scarcity of labelled training data. Additionally, there is often class imbalance in datasets…

In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related…

Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities. When domain distribution changes, the vulnerability of…

Federated learning (FL) faces challenges in uncertainty quantification (UQ). Without reliable UQ, FL systems risk deploying overconfident models at under-resourced agents, leading to silent local failures despite seemingly satisfactory…