Supplementary Material of ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
نویسندگان
چکیده
Since our paper constrain correlation of two random variables using information theoretical measures, we first review the related concepts. For any probability measure π on the random variables x and z, we have the following additive and subtractive relationships for various information measures, including Mutual Information (MI), Variation of Information (VI) and the Conditional Entropy (CE). VI(x, z) =− Eπ(z,x)[log π(x|z)]− Eπ(x,z)[log π(z|x)] (1)
منابع مشابه
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We unify a broad family of adversarial models as joint distribution matching pr...
متن کاملTowards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We unify a broad family of adversarial models as joint distribution matching pr...
متن کاملSemi-Supervised Learning for Optical Flow with Generative Adversarial Networks Supplementary Material
In this supplementary document, we present additional results to complement the paper. First, we provide the detailed configurations and parameters of the generator and discriminator in the proposed Generative Adversarial Network. Second, we present the qualitative comparisons with the state-ofthe-art CNN-based optical flow methods. The complete results and source code are publicly available on...
متن کاملCrossing Generative Adversarial Networks for Cross-View Person Re-identification
Person re-identification (re-id) refers to matching pedestrians across disjoint yet non-overlapping camera views. The most effective way to match these pedestrians undertaking significant visual variations is to seek reliably invariant features that can describe the person of interest faithfully. Most of existing methods are presented in a supervised manner to produce discriminative features by...
متن کاملTriangle Generative Adversarial Networks
A Triangle Generative Adversarial Network (∆-GAN) is developed for semisupervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. ∆-GAN consists of four neural networks, two generators and two discriminators. The generators are designed to learn the two-way ...
متن کامل