SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single invertible transport over the full ambient space, making them highly sensitive to high-dimensional representations. This leads to a semantic-capacity mismatch in modern visual representation spaces, where semantic information is compact but encoded in overcomplete features. We propose SRC-Flow, which introduces a Semantic Representation Compressor (SRC) to compact high-dimensional RAE features into a low-dimensional semantic space before flow modeling and preserve reconstruction through the frozen RAE decoder. This compact space reduces the modeling burden of NFs and enables effective likelihood-based generation in semantic representation space. We further adopt constant noise regularization tailored to the fixed unconditional bijection learned by flows. On ImageNet $256 \times 256$ and $512 \times 512$, SRC-Flow achieves state-of-the-art generation quality among normalizing flow methods, with gFID scores of 1.65 and 2.07 under classifier-free guidance, while retaining exact likelihood computation in the compact semantic representation space and deterministic invertible sampling at the flow level. Codes and models will be available at https://github.com/longtaojiang/SRC-Flow.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Ordering Dimensions with Nested Dropout Normalizing Flows
The latent space of normalizing flows must be of the same dimensionality as their output space. This constraint presents a problem if we want to learn low-dimensional, semantically meaningful representations. Recent work…
From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows
Learning unsupervised representations that are both semantically meaningful and stable across runs remains a central challenge in modern representation learning. We introduce entropy-ordered flows (EOFlows), a normalizin…
Representation LearningBoosting Summarization with Normalizing Flows and Aggressive Training
This paper presents FlowSUM, a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization. Our approach tackles two primary challenges in variational summarization: insufficient sem…
DecoderKnowledge DistillationText SummarizationUnsupervised Learning of PCFGs with Normalizing Flow
Unsupervised PCFG inducers hypothesize sets of compact context-free rules as explanations for sentences. PCFG induction not only provides tools for low-resource languages, but also plays an important role in modeling lan…
Language AcquisitionLatent Reasoning with Normalizing Flows
Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. However, textual CoT forces this computation through a discrete, seri…