paper-with-me

홈 › Papers

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation

2023-02-27 · ICCV 2023 1 · Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, WangMeng Zuo

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet bringing excessive computation or memory burden. In this paper, we instead propose a learning-based encoder, which consists of a global and a local mapping networks for fast and accurate customized text-to-image generation. In specific, the global mapping network projects the hierarchical features of a given image into multiple new words in the textual word embedding space, i.e., one primary word for well-editable concept and other auxiliary words to exclude irrelevant disturbances (e.g., background). In the meantime, a local mapping network injects the encoded patch features into cross attention layers to provide omitted details, without sacrificing the editability of primary concepts. We compare our method with existing optimization-based approaches on a variety of user-defined concepts, and demonstrate that our method enables high-fidelity inversion and more robust editability with a significantly faster encoding process. Our code is publicly available at https://github.com/csyxwei/ELITE.

📄 PDF Abstract BibTeX arXiv:2302.13848

Code (2)

csyxwei/elite 공식 구현 pytorch
lukemelas/realfusion pytorch

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining

2025-01-27 · Ruiqi Wu, Na Su, Chenran Zhang, Tengfei Ma 외

Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievements, they significantly rely on large-s…

Contrastive LearningTransfer Learning

MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding

2020-01-11 · Geondo Park, Chihye Han, Wonjun Yoon, Dae-shik Kim

Visual-semantic embedding enables various tasks such as image-text retrieval, image captioning, and visual question answering. The key to successful visual-semantic embedding is to express visual and textual data properl…

Image CaptioningImage-text RetrievalQuestion AnsweringRetrieval+3

Learning Unseen Concepts via Hierarchical Decomposition and Composition

2020-06-01 · CVPR 2020 6 · Muli Yang, Cheng Deng, Junchi Yan, Xianglong Liu 외

Composing and recognizing new concepts from known sub-concepts has been a fundamental and challenging vision task, mainly due to 1) the diversity of sub-concepts and 2) the intricate contextuality between sub-concepts an…

Diversity

EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search

2020-09-16 · Ching-Chen Wang, Ching-Te Chiu, Jheng-Yi Chang

Embedding Convolutional Neural Network (CNN) into edge devices for inference is a very challenging task because such lightweight hardware is not born to handle this heavyweight software, which is the common overhead from…

Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders

2026-06-19 · Sergio Lanza, Jae Hee Lee, Stefan Wermter arxiv

Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioning and Visual Question Answering (VQA), but our understanding of the…

Visual Question AnsweringImage Captioning