paper-with-me

홈 › Papers

The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation

2022-11-22 · ICCV 2023 1 · Lingxiao Li, Yi Zhang, Shuhui Wang

Few-shot image generation is a challenging task since it aims to generate diverse new images for an unseen category with only a few images. Existing methods suffer from the trade-off between the quality and diversity of generated images. To tackle this problem, we propose Hyperbolic Attribute Editing~(HAE), a simple yet effective method. Unlike other methods that work in Euclidean space, HAE captures the hierarchy among images using data from seen categories in hyperbolic space. Given a well-trained HAE, images of unseen categories can be generated by moving the latent code of a given image toward any meaningful directions in the Poincar\'e disk with a fixing radius. Most importantly, the hyperbolic space allows us to control the semantic diversity of the generated images by setting different radii in the disk. Extensive experiments and visualizations demonstrate that HAE is capable of not only generating images with promising quality and diversity using limited data but achieving a highly controllable and interpretable editing process.

📄 PDF Abstract BibTeX arXiv:2211.12347

Code (1)

lingxiao-li/hae 공식 구현 pytorch

Tasks

AttributeDiversityImage Generation

Similar Papers 제목 키워드 기반

Consistent Spectral Clustering in Hyperbolic Spaces

2024-09-14 · Sagar Ghosh, Swagatam Das

Clustering, as an unsupervised technique, plays a pivotal role in various data analysis applications. Among clustering algorithms, Spectral Clustering on Euclidean Spaces has been extensively studied. However, with the r…

Clustering

Combined Hyperbolic and Euclidean Soft Triple Loss Beyond the Single Space Deep Metric Learning

2025-10-07 · Shozo Saeki, Minoru Kawahara, Hirohisa Aman arxiv

Deep metric learning (DML) aims to learn a neural network mapping data to an embedding space, which can represent semantic similarity between data points. Hyperbolic space is attractive for DML since it can represent ric…

Semantic SimilarityMetric Learning

Hyperbolic Diffusion Recommender Model

2025-04-02 · Meng Yuan, Yutian Xiao, Wei Chen, Chu Zhao 외

Diffusion models (DMs) have emerged as the new state-of-the-art family of deep generative models. To gain deeper insights into the limitations of diffusion models in recommender systems, we investigate the fundamental st…

modelRecommendation Systems

Model Editing with Graph-Based External Memory

2025-05-23 · Yash Kumar Atri, Ahmed Alaa, Thomas Hartvigsen

Large language models (LLMs) have revolutionized natural language processing, yet their practical utility is often limited by persistent issues of hallucinations and outdated parametric knowledge. Although post-training …

graph constructionmodelModel Editing

Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers

2021-07-23 · CVPR 2022 1 · Yunhui Guo, Xudong Wang, Yubei Chen, Stella X. Yu

Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outp…

Adversarial RobustnessGeneral ClassificationOut-of-Distribution Detection