paper-with-me

홈 › Papers

Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs

2020-02-25 · Sangwoo Mo, Minsu Cho, Jinwoo Shin

Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources. To tackle this issue, several methods introduce a transfer learning technique in GAN training. They, however, are either prone to overfitting or limited to learning small distribution shifts. In this paper, we show that simple fine-tuning of GANs with frozen lower layers of the discriminator performs surprisingly well. This simple baseline, FreezeD, significantly outperforms previous techniques used in both unconditional and conditional GANs. We demonstrate the consistent effect using StyleGAN and SNGAN-projection architectures on several datasets of Animal Face, Anime Face, Oxford Flower, CUB-200-2011, and Caltech-256 datasets. The code and results are available at https://github.com/sangwoomo/FreezeD.

📄 PDF Abstract BibTeX arXiv:2002.10964

Code (4)

sangwoomo/freezeD 공식 구현 pytorch
eps696/stylegan2 tf
husnain-ali21/Image_Generation_using_StyleGAN pytorch
uzielroy/StyleGan_FewShot pytorch

Tasks

10-shot image generationImage GenerationTransfer Learning

Methods 이 논문이 사용한 방법론

Adaptive Instance Normalization 설명 없음
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…
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…
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…
StyleGAN 설명 없음
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…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer

2021-07-21 · ACL (MetaNLP) 2021 8 · Weijia Xu, Batool Haider, Jason Krone, Saab Mansour

Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune thes…

Cross-Lingual Natural Language InferenceCross-Lingual TransferMeta-LearningNatural Language Inference+1

AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning

2021-02-02 · YuHan Liu, Saurabh Agarwal, Shivaram Venkataraman

With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data. However, our experiments show that even fine-tuning on mo…

GPU

Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models

2024-03-26 · Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi, Kyunggeun Lee 외

Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory require…

Knowledge DistillationQuantization

Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block

2021-10-11 · Durvesh Malpure, Onkar Litake, Rajesh Ingle

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, t…

Transfer Learning

ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling

2026-06-30 · Konstantinos Georgiou, Maofeng Tang, Hairong Qi arxiv

Multi-objective masked image modeling (MIM) combines complementary learning signals (token distillation, CLS alignment, and pixel reconstruction) but existing methods weight these objectives with global scalars, ignoring…