paper-with-me

Papers

Boundary-Seeking Generative Adversarial Networks

2017-02-27 · R. Devon Hjelm, Athul Paul Jacob, Tong Che, Adam Trischler, Kyunghyun Cho, Yoshua Bengio

Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importance weights have a strong connection to the decision boundary of the discriminator, and we call our method boundary-seeking GANs (BGANs). We demonstrate the effectiveness of the proposed algorithm with discrete image and character-based natural language generation. In addition, the boundary-seeking objective extends to continuous data, which can be used to improve stability of training, and we demonstrate this on Celeba, Large-scale Scene Understanding (LSUN) bedrooms, and Imagenet without conditioning.

📄 PDF Abstract BibTeX arXiv:1702.08431

Code (6)

MichalKacprzak99/reconstruction_particle_mass_spectra tf
eriklindernoren/Keras-GAN pytorch
eriklindernoren/PyTorch-GAN pytorch
kklemon/bgan-pytorch pytorch
lvyufeng/MindSpore-GAN mindspore
rdevon/BGAN

Tasks

Scene UnderstandingText Generation

Similar Papers 제목 키워드 기반

Boundary Seeking GANs

2018-01-01 · ICLR 2018 1 · R. Devon Hjelm, Athul Paul Jacob, Adam Trischler, Gerry Che 외

Generative adversarial networks are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the g…

Scene UnderstandingText Generation

On the Failure of Boundary-Seeking Distillation in Bottlenecked Generative Architectures

2026-07-17 · Mohamed Amine Kina arxiv

Data-free knowledge distillation transfers the knowledge encoded in a teacher model to a student model without access to the original training data. Prior work such as Contrastive Abductive Knowledge Extraction (CAKE) ac…

Data-free Knowledge Distillation

ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning

2022-11-08 · Eddy Hudson, Ishan Durugkar, Garrett Warnell, Peter Stone

Given a dataset of expert agent interactions with an environment of interest, a viable method to extract an effective agent policy is to estimate the maximum likelihood policy indicated by this data. This approach is com…

Generative Adversarial NetworkImitation Learning

Difference-Seeking Generative Adversarial Network

2019-05-01 · ICLR 2019 5 · Yi-Lin Sung, Sung-Hsien Hsieh, Soo-Chang Pei, Chun-Shien Lu

We propose a novel algorithm, Difference-Seeking Generative Adversarial Network (DSGAN), developed from traditional GAN. DSGAN considers the scenario that the training samples of target distribution, $p_{t}$, are difficu…

Generative Adversarial Network

Disentangling Adversarial Robustness in Directions of the Data Manifold

2021-01-01 · Jiancong Xiao, Liusha Yang, Zhi-Quan Luo

Using generative models (GAN or VAE) to craft adversarial examples, i.e. generative adversarial examples, has received increasing attention in recent years. Previous studies showed through experiments that the generative…

Adversarial Robustness