paper-with-me

Papers

On the Importance of Noise Scheduling for Diffusion Models

2023-01-26 · Ting Chen

We empirically study the effect of noise scheduling strategies for denoising diffusion generative models. There are three findings: (1) the noise scheduling is crucial for the performance, and the optimal one depends on the task (e.g., image sizes), (2) when increasing the image size, the optimal noise scheduling shifts towards a noisier one (due to increased redundancy in pixels), and (3) simply scaling the input data by a factor of $b$ while keeping the noise schedule function fixed (equivalent to shifting the logSNR by $\log b$) is a good strategy across image sizes. This simple recipe, when combined with recently proposed Recurrent Interface Network (RIN), yields state-of-the-art pixel-based diffusion models for high-resolution images on ImageNet, enabling single-stage, end-to-end generation of diverse and high-fidelity images at 1024$\times$1024 resolution (without upsampling/cascades).

📄 PDF Abstract BibTeX arXiv:2301.10972

Code (2)

google-research/pix2seq tf
lucidrains/recurrent-interface-network-pytorch pytorch

Tasks

DenoisingScheduling

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data

2025-08-01 · Timur Sattarov, Marco Schreyer, Damian Borth arxiv

Anomaly detection in tabular data remains challenging due to complex feature interactions and the scarcity of anomalous examples. Denoising autoencoders rely on fixed-magnitude noise, limiting adaptability to diverse dat…

Contrastive LearningAnomaly Detection

Noise scheduling and linear dynamics in diffusion models on Lie groups

2026-05-17 · Javad Komijani arxiv

We investigate the role of the noise schedule in diffusion processes on Lie groups, with particular emphasis on applications to lattice gauge theory. We show that a specific noise schedule leads to a linear decay of the …

Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration

2024-10-17 · Yun-Yen Chuang, Hung-Min Hsu, Kevin Lin, Chen-Sheng Gu 외

The diffusion model, a new generative modeling paradigm, has achieved significant success in generating images, audio, video, and text. It has been adapted for sequence-to-sequence text generation (Seq2Seq) through Diffu…

DenoisingSchedulingSentenceText Generation

Diffusion Model-Based Multiobjective Optimization for Gasoline Blending Scheduling

2024-02-04 · Wenxuan Fang, Wei Du, Renchu He, Yang Tang 외

Gasoline blending scheduling uses resource allocation and operation sequencing to meet a refinery's production requirements. The presence of nonlinearity, integer constraints, and a large number of decision variables add…

Evolutionary AlgorithmsMultiobjective OptimizationScheduling

Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning

2023-05-26 · Yuchang Sun, Zehong Lin, Yuyi Mao, Shi Jin 외

Federated learning (FL) is a popular privacy-preserving distributed training scheme, where multiple devices collaborate to train machine learning models by uploading local model updates. To improve communication efficien…

Federated LearningPrivacy PreservingScheduling