Why Are Conditional Generative Models Better Than Unconditional Ones?
Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data. So do score-based diffusion models. In this paper, we analyze the phenomenon formally and identify that the key of conditional learning is to partition the data properly. Inspired by the analyses, we propose self-conditioned diffusion models (SCDM), which is trained conditioned on indices clustered by the k-means algorithm on the features extracted by a model pre-trained in a self-supervised manner. SCDM significantly improves the unconditional model across various datasets and achieves a record-breaking FID of 3.94 on ImageNet 64x64 without labels. Besides, SCDM achieves a slightly better FID than the corresponding conditional model on CIFAR10.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Return of Unconditional Generation: A Self-supervised Representation Generation Method
Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from …
Conditional Image GenerationImage GenerationUnconditional Image GenerationTheoretical Insights into the Use of Structural Similarity Index In Generative Models and Inferential Autoencoders
Generative models and inferential autoencoders mostly make use of $\ell_2$ norm in their optimization objectives. In order to generate perceptually better images, this short paper theoretically discusses how to use Struc…
Dimensionality ReductionImage GenerationImage Quality AssessmentSSIMScore-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
Score-based generative models (SGMs) are a popular family of deep generative models that achieve leading image generation quality. Early studies extend SGMs to tackle class-conditional generation by coupling an unconditi…
Image GenerationDistance Marching for Generative Modeling
Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and different denoising directions, which i…
Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Trees
Generating novel molecules is challenging, with most representations leading to generative models producing many invalid molecules. Spanning Tree-based Graph Generation (STGG) is a promising approach to ensure the genera…
Graph GenerationProperty Predictionvalid