Named Entity Driven Zero-Shot Image Manipulation
We introduced StyleEntity a zero-shot image manipulation model that utilizes named entities as proxies during its training phase. This strategy enables our model to manipulate images using unseen textual descriptions during inference all within a single training phase. Additionally we proposed an inference technique termed Prompt Ensemble Latent Averaging (PELA). PELA averages the manipulation directions derived from various named entities during inference effectively eliminating the noise directions thus achieving stable manipulation. In our experiments StyleEntity exhibited superior performance in a zero-shot setting compared to other methods. The code model weights and datasets is available at https://github.com/feng-zhida/StyleEntity.
Code (1)
Tasks
Image ManipulationSimilar Papers 제목 키워드 기반
Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification
A common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for the target entity classes during training. Zero-shot learning approaches address this i…
Machine Reading Comprehensionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+6Label Embedding for Zero-shot Fine-grained Named Entity Typing
Named entity typing is the task of detecting the types of a named entity in context. For instance, given {``}Eric is giving a presentation{''}, our goal is to infer that {`}Eric{'} is a speaker or a presenter and a perso…
Entity LinkingEntity TypingNamed Entity Recognition (NER)Question Answering+2ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models
This paper presents ReverseNER, a method aimed at overcoming the limitation of large language models (LLMs) in zero-shot named entity recognition (NER) tasks, arising from their reliance on pre-provided demonstrations. R…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+2Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantifying Label Shifts in Synthetic Training Data
Zero-shot named entity recognition (NER) is the task of detecting named entities of specific types (such as 'Person' or 'Medicine') without any training examples. Current research increasingly relies on large synthetic d…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+3Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework
In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings. Built upon large-scale pre-trained language models, we propose a novel NER fra…
Few-Shot Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2