SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
SAGE 利用視覺基礎表示發現目標數據集中的顯著因素,並根據參考圖像的顯著表示引導生成新例子。在 Digits-ImageNet 和 FFHQ 眼鏡數據集上,SAGE 的重建 rFID 低於 2,並能在沒有子類別標籤的情況下發現子類別;Digits-ImageNet 的探測準確率達 0.950,優於基線的最高 0.281。
Published on Sep 30
Authors:
,
,
,
,
,
,
Abstract
Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates salient factors specific to the target from common content shared by both. We aim for salient representations that capture target-specific detail in each image, such as the shape, color, and position of the glasses, so that they reveal subtypes without subtype labels and guide the generation of new examples of a discovered subtype, even one with no name or text description. We introduce SAGE, which learns both factors directly in the high-dimensional spatial latent of a frozen representation autoencoder and conditions a diffusion transformer on the learned salient representation of a reference image. On Digits-ImageNet and FFHQ eyeglasses, SAGE combines high-fidelity reconstruction (rFID below 2) with unsupervised subtype discovery, recovering the digits better than baselines (probe accuracy 0.950 vs.\ at most 0.281) and revealing eyewear types, finer sunglasses styles, and mislabeled images; salient-conditioned generation raises Digits-ImageNet subtype accuracy over the unfactorized latent (90.5% vs.\ 27.7%) and diversity on both datasets. On retinal OCT, SAGE's salient space separates three diseases using only normal/disease labels.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2609.39635
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2609.39635 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2609.39635 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2609.39635 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co