There and Back Again: On the relation between noises, images, and their inversions in diffusion models
Denoising Diffusion Probabilistic Models (DDPMs) achieve state-of-the-art performance in synthesizing new images from random noise, but they lack meaningful latent space that encodes data into features. Recent DDPM-based editing techniques try to mitigate this issue by inverting images back to their approximated staring noise. In this work, we study the relation between the initial Gaussian noise, the samples generated from it, and their corresponding latent encodings obtained through the inversion procedure. First, we interpret their spatial distance relations to show the inaccuracy of the DDIM inversion technique by localizing latent representations manifold between the initial noise and generated samples. Then, we demonstrate the peculiar relation between initial Gaussian noise and its corresponding generations during diffusion training, showing that the high-level features of generated images stabilize rapidly, keeping the spatial distance relationship between noises and generations consistent throughout the training.
Code (1)
Tasks
DenoisingRelationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses, but there are no comprehensive studies of how …
Adversarial RobustnessBenchmarkingData AugmentationNeural Architecture SearchImplicit Regularization Effects of Unbiased Random Label Noises with SGD
Random label noises (or observational noises) widely exist in practical machinelearning settings. we analyze the learning dynamics of stochastic gradient descent(SGD) over the quadratic loss with unbiased label noises, a…
Denoising Diffusion Recommender Model
Recommender systems often grapple with noisy implicit feedback. Most studies alleviate the noise issues from data cleaning perspective such as data resampling and reweighting, but they are constrained by heuristic assump…
DenoisingmodelRecommendation SystemsRepresentation LearningGradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks
Modern neural networks are usually highly over-parameterized. Behind the wide usage of over-parameterized networks is the belief that, if the data are simple, then the trained network will be automatically equivalent to …
Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network
Automatically detecting sound units of humpback whales in complex time-varying background noises is a current challenge for scientists. In this paper, we explore the applicability of Convolution Neural Network (CNN) meth…
General Classification