Comments (1)
Summary:
- Dataset: SVHN, MNIST, USPS, CIFAR and STL.
- Objective: Build a network easily trainable by back-propagation to perform unsupervised domain adaptation while at the same time learning a good embedding for both source and target domains.
Architecture:
Very similar to RevGrad but with some differences.
Basically a shared encoder and then a classifier and a reconstructor.
The two losses are:
- the usual cross-entropy with softmax for the classifier
- the pixel-wise squared loss for reconstruction
Which are then combined using a trade-off hyper-parameter between classification and reconstruction.
They also use data augmentation to generate additional training data during the supervised training using only geometrical deformation: translation, rotation, skewing, and scaling
Plus denoising to reconstruct clean inputs given their noisy counterparts (zero-masked noise and Gaussian noise).
Results:
Outperforms state of the art on most tasks at the time, now outperformed itself by Generate To Adapt on most tasks.
from papers.
Related Issues (20)
- Neural Episodic Control HOT 1
- Generate To Adapt - Aligning Domains using Generative Adversarial Networks HOT 1
- Softmax GAN HOT 1
- Visual Attribute Transfer through Deep Image Analogy HOT 1
- Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction HOT 1
- Neural Architecture Search with Reinforcement Learning HOT 1
- Deep Residual Learning for Image Recognition HOT 1
- Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space HOT 1
- Domain Adaptation with Randomized Multilinear Adversarial Networks HOT 1
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks HOT 1
- Self-Normalizing Neural Networks HOT 1
- Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks HOT 1
- Active Learning Literature Survey HOT 1
- Active Learning by Learning HOT 1
- StreetStyle: Exploring world-wide clothing styles from millions of photos HOT 1
- pix2code: Generating Code from a Graphical User Interface Screenshot HOT 1
- Speed/accuracy trade-offs for modern convolutional object detectors HOT 1
- Training Deep Neural Networks on Noisy Labels with Bootstrapping HOT 1
- A System for Accessible Artificial Intelligence HOT 1
- Cost-Effective Active Learning for Deep Image Classification HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from papers.