paper-with-me

Papers

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines

2024-03-09 · Michael Toker, Hadas Orgad, Mor Ventura, Dana Arad, Yonatan Belinkov

Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text representation is unknown. We propose the Diffusion Lens, a method for analyzing the text encoder of T2I models by generating images from its intermediate representations. Using the Diffusion Lens, we perform an extensive analysis of two recent T2I models. Exploring compound prompts, we find that complex scenes describing multiple objects are composed progressively and more slowly compared to simple scenes; Exploring knowledge retrieval, we find that representation of uncommon concepts requires further computation compared to common concepts, and that knowledge retrieval is gradual across layers. Overall, our findings provide valuable insights into the text encoder component in T2I pipelines.

📄 PDF Abstract BibTeX arXiv:2403.05846

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationRetrieval

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

Decoding Vision Transformers: the Diffusion Steering Lens

2025-04-18 · Ryota Takatsuki, Sonia Joseph, Ippei Fujisawa, Ryota Kanai

Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output v…

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning

2025-05-30 · Stepan Shabalin, Ayush Panda, Dmitrii Kharlapenko, Abdur Raheem Ali 외

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diff…

Dictionary LearningImage GenerationLanguage ModelingLanguage Modelling

Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge

2024-10-16 · Fawaz Sammani, Nikos Deligiannis

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This…

Classificationimage-classificationImage Classificationzero-shot-classification+2

Schödinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders

2024-12-24 · Kentaro Kaba, Reo Shimizu, Masayuki Ohzeki, Yuki Sughiyama

Generative diffusion models use time-forward and backward stochastic differential equations to connect the data and prior distributions. While conventional diffusion models (e.g., score-based models) only learn the backw…

$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models

2024-11-23 · Dahye Kim, Xavier Thomas, Deepti Ghadiyaram

We study $\textit{how}$ rich visual semantic information is represented within various layers and denoising timesteps of different diffusion architectures. We uncover monosemantic interpretable features by leveraging k-s…

DenoisingLanguage ModelingLanguage ModellingRepresentation Learning+1