paper-with-me

홈 › Papers

PAGER: Progressive Attribute-Guided Extendable Robust Image Generation

2022-06-01 · Zohreh Azizi, C. -C. Jay Kuo

This work presents a generative modeling approach based on successive subspace learning (SSL). Unlike most generative models in the literature, our method does not utilize neural networks to analyze the underlying source distribution and synthesize images. The resulting method, called the progressive attribute-guided extendable robust image generative (PAGER) model, has advantages in mathematical transparency, progressive content generation, lower training time, robust performance with fewer training samples, and extendibility to conditional image generation. PAGER consists of three modules: core generator, resolution enhancer, and quality booster. The core generator learns the distribution of low-resolution images and performs unconditional image generation. The resolution enhancer increases image resolution via conditional generation. Finally, the quality booster adds finer details to generated images. Extensive experiments on MNIST, Fashion-MNIST, and CelebA datasets are conducted to demonstrate generative performance of PAGER.

📄 PDF Abstract BibTeX arXiv:2206.00162

Code (1)

zohrehazizi/torch_ssl 공식 구현 pytorch

Tasks

AttributeConditional Image GenerationImage GenerationUnconditional Image Generation

Similar Papers 제목 키워드 기반

1-PAGER: One Pass Answer Generation and Evidence Retrieval

2023-10-25 · Palak Jain, Livio Baldini Soares, Tom Kwiatkowski

We present 1-Pager the first system that answers a question and retrieves evidence using a single Transformer-based model and decoding process. 1-Pager incrementally partitions the retrieval corpus using constrained deco…

Answer GenerationQuestion AnsweringRetrieval

Learning Disentangled Representation for One-shot Progressive Face Swapping

2022-03-24 · Qi Li, Weining Wang, Chengzhong Xu, Zhenan Sun 외

Although face swapping has attracted much attention in recent years, it remains a challenging problem. Existing methods leverage a large number of data samples to explore the intrinsic properties of face swapping without…

AttributeDisentanglementFace Swapping

Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning

2026-07-07 · Ziyi Chen, Haoyan Shi, Sunhan Xu, Congyan Lang arxiv

Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently…

Compositional Zero-Shot LearningReinforcement Learning

Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion

2025-03-25 · Chang Chen, Hany Hamed, Doojin Baek, Taegu Kang 외

This paper tackles a novel problem, extendable long-horizon planning-enabling agents to plan trajectories longer than those in training data without compounding errors. To tackle this, we propose the Hierarchical Multisc…

P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation

2025-05-21 · Zhenyan Yao, Miao Zhang, Lanhu Wu, Yongri Piao 외

Perturbation with diverse unlabeled data has proven beneficial for semi-supervised medical image segmentation (SSMIS). While many works have successfully used various perturbation techniques, a deeper understanding of le…

Image SegmentationMedical Image SegmentationSemantic SegmentationSemi-supervised Medical Image Segmentation