Unsupervised Transfer

Generate To Adapt: Aligning Domains using Generative Adversarial Networks

1.Main

using unlabeled target data help transfer(target image&class seen)

2.structure

3. Loss Func

Source Data: D: G:

C&F:

Target data

4.DataSet

Digit classification (MNIST, SVHN and USPS datasets)Object recognition using OFFICE datasetsDomain adaptation from synthetic to real data;CAD synthetic dataset (source) and a subset of PASCAL VOC dataset(target)VISDA dataset:Trasfer competation

5.metric

classification accurancy

Disentangled Classification and Reconstruction for Zero-shot learning

Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks

1.Main

prevents the semantic loss while target image&class unseen

2. Structure

3. Loss Func

Class loss Reconstruction Loss 3.Adversarial Loss

4.Dataset

CUB, AWA, SUN and aPY, SP-AEN

5.Metric

harmonic mean (H) on generalized ZSL The Seen-Unseen accuracy Curve (SUC)

Conditional GAN on feature space

Adversarial Feature Augmentation for Unsupervised Domain Adaptation

1.Main

Gener new feature vec for augmentation

2.Structure

3.Loss Func

S1 Train reference feature encoder E_S Classfier C in Source dataS2 Conditional Gan for gener new feature vec in Source domain,get Encoder SS3 Train encoder in T&S advertising with S

4.Datasets

mnist ,usps :white digit on black backgroundsvhn:real images of street view house numberssyn digits:syn on svhnnyud:object RGB->D

5.Metric

t-SNEAPs:feature augmentationAccuracy:compare with C trained on S,T,Other method