텍스트-이미지 모델, 텍스트 인코더의 단순 정보만 활용
Text-to-Image Models Need Less from Text Encoders Than You Think
- 매체
- Hugging Face
- 게시
- 중요도
- 3/5
- 화제 지수
- 3
한국어 요약
텍스트-이미지 확산 모델이 텍스트 인코더의 풍부한 문맥 정보를 실제로는 활용하지 않는다는 연구 결과가 발표됐다. 단어 의미와 단어 순서만 인코딩한 간단한 표현으로도 기존 전체 텍스트 임베딩과 동등한 이미지 생성 품질을 달성할 수 있음을 보였다.
원문 발췌 · English
Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation process. Beyond individual token meanings, text embeddings encode contextual information across the full prompt, such as compositionality and attribute binding. However, whether image models actually exploit this richer information remains underexplored. Here, we address the question: Which aspects of text representation are essential for image generation? We show that text-to-image diffusion transformer-based models commonly rely only on two relatively straightforward aspects of text representations: (i) the merging of adjacent tokens into a word representation, for words spanning multiple tokens, and (ii) word order, which is imprinted by the positional embedding of the text-encoder. To show this, we construct a new text embedding that encodes only individual word meanings and order but lacks any contextual information about the full prompt. We find that this bag of position-tagged words representation is sufficient to successfully guide image generation, achieving visual quality and text fidelity that are on par with full text embedding-guided generation. This demonstrates that, contrary to common belief, text-to-image models often do not use the rich information encoded in the text embedding beyond individual word meanings and word order. Instead, the decoding of complex linguistic structures is performed by the image model itself. Project webpage: https://nsping13.github.io/contextless-TTI/