paper-with-me

홈 › Papers

HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation

2024-11-19 · Abdul Basit Anees, Ahmet Canberk Baykal, Muhammed Burak Kizil, Duygu Ceylan, Erkut Erdem, Aykut Erdem

Generative Adversarial Networks (GANs), particularly StyleGAN and its variants, have demonstrated remarkable capabilities in generating highly realistic images. Despite their success, adapting these models to diverse tasks such as domain adaptation, reference-guided synthesis, and text-guided manipulation with limited training data remains challenging. Towards this end, in this study, we present a novel framework that significantly extends the capabilities of a pre-trained StyleGAN by integrating CLIP space via hypernetworks. This integration allows dynamic adaptation of StyleGAN to new domains defined by reference images or textual descriptions. Additionally, we introduce a CLIP-guided discriminator that enhances the alignment between generated images and target domains, ensuring superior image quality. Our approach demonstrates unprecedented flexibility, enabling text-guided image manipulation without the need for text-specific training data and facilitating seamless style transfer. Comprehensive qualitative and quantitative evaluations confirm the robustness and superior performance of our framework compared to existing methods.

📄 PDF Abstract BibTeX arXiv:2411.12832

Code (1)

adobe-research/domain-expansion 공식 구현 pytorch

Tasks

Domain AdaptationImage GenerationImage ManipulationStyle Transfer

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Adaptive Instance Normalization 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
StyleGAN 설명 없음

Similar Papers 제목 키워드 기반

HyperGAN: Exploring the Manifold of Neural Networks

2018-09-27 · Neale Ratzlaff, Li Fuxin

We introduce HyperGAN, a generative network that learns to generate all the weight parameters of deep neural networks. HyperGAN first transforms low dimensional noise into a latent space, which can be sampled from to obt…

HyperGAN: A Generative Model for Diverse, Performant Neural Networks

2019-01-30 · Neale Ratzlaff, Li Fuxin

Standard neural networks are often overconfident when presented with data outside the training distribution. We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters. HyperGA…

General Classification

UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptation

2024-01-23 · Hengjia Li, Yang Liu, Yuqi Lin, Zhanwei Zhang 외

Recently, generative domain adaptation has achieved remarkable progress, enabling us to adapt a pre-trained generator to a new target domain. However, existing methods simply adapt the generator to a single target domain…

AttributeDiversityDomain Adaptation

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

2024-03-11 · CVPR 2024 1 · Xinyao Li, Yuke Li, Zhekai Du, Fengling Li 외

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visua…

Domain AdaptationUnsupervised Domain AdaptationZero-Shot Learning

Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation

2024-04-09 · Sidra Aleem, Fangyijie Wang, Mayug Maniparambil, Eric Arazo 외

The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero …

Image SegmentationMedical Image SegmentationOrgan SegmentationPrompt Engineering+5