paper-with-me

홈 › Papers

Diverse Rare Sample Generation with Pretrained GANs

2024-12-27 · SuBeen Lee, Jiyeon Han, Soyeon Kim, Jaesik Choi

Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent methods aim to improve the fidelity of generated samples, they often reduce diversity and coverage by ignoring rare and novel samples. This study proposes a novel approach for generating diverse rare samples from high-resolution image datasets with pretrained GANs. Our method employs gradient-based optimization of latent vectors within a multi-objective framework and utilizes normalizing flows for density estimation on the feature space. This enables the generation of diverse rare images, with controllable parameters for rarity, diversity, and similarity to a reference image. We demonstrate the effectiveness of our approach both qualitatively and quantitatively across various datasets and GANs without retraining or fine-tuning the pretrained GANs.

📄 PDF Abstract BibTeX arXiv:2412.19543

Code (1)

sbrblee/DivRareGen 공식 구현 pytorch

Tasks

Density EstimationDiversity

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Transferring GANs: generating images from limited data

2018-05-04 · ECCV 2018 9 · Yaxing Wang, Chenshen Wu, Luis Herranz, Joost Van de Weijer 외

Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been s…

10-shot image generationDiversityDomain AdaptationImage Generation

Transferring Unconditional to Conditional GANs with Hyper-Modulation

2021-12-04 · Héctor Laria, Yaxing Wang, Joost Van de Weijer, Bogdan Raducanu

GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study o…

Conditional Image GenerationContrastive LearningTransfer Learning

ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generation

2023-07-11 · Fadi Boutros, Marcel Klemt, Meiling Fang, Arjan Kuijper 외

Deep generative models have recently presented impressive results in generating realistic face images of random synthetic identities. To generate multiple samples of a certain synthetic identity, previous works proposed …

AttributeFace Recognition

Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement

2024-03-24 · Yuxuan Wang, Xiaoyuan Liu

Scene Graph Generation (SGG) provides basic language representation of visual scenes, requiring models to grasp complex and diverse semantics between objects. This complexity and diversity in SGG leads to underrepresenta…

DiversityGraph GenerationRelationScene Graph Generation+1

Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?

2022-01-17 · Hwanil Choi, Wonjoon Chang, Jaesik Choi

Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic images. Occasionally, they generate images…

GAN image forensicsImage GenerationImage ManipulationImage Reconstruction