Overcoming Mode Collapse with Adaptive Multi Adversarial Training
- URL: http://arxiv.org/abs/2112.14406v1
- Date: Wed, 29 Dec 2021 05:57:55 GMT
- Title: Overcoming Mode Collapse with Adaptive Multi Adversarial Training
- Authors: Karttikeya Mangalam, Rohin Garg
- Abstract summary: Generative Adversarial Networks (GANs) are a class of generative models used for various applications.
GANs have been known to suffer from the mode collapse problem, in which some modes of the target distribution are ignored by the generator.
We introduce a novel training procedure that adaptively spawns additional discriminators to remember previous modes of generation.
- Score: 5.09817514580101
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generative Adversarial Networks (GANs) are a class of generative models used
for various applications, but they have been known to suffer from the mode
collapse problem, in which some modes of the target distribution are ignored by
the generator. Investigative study using a new data generation procedure
indicates that the mode collapse of the generator is driven by the
discriminator's inability to maintain classification accuracy on previously
seen samples, a phenomenon called Catastrophic Forgetting in continual
learning. Motivated by this observation, we introduce a novel training
procedure that adaptively spawns additional discriminators to remember previous
modes of generation. On several datasets, we show that our training scheme can
be plugged-in to existing GAN frameworks to mitigate mode collapse and improve
standard metrics for GAN evaluation.
Related papers
- GUIDE: Guidance-based Incremental Learning with Diffusion Models [3.046689922445082]
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten.
Our experimental results show that GUIDE significantly reduces catastrophic forgetting, outperforming conventional random sampling approaches and surpassing recent state-of-the-art methods in continual learning with generative replay.
arXiv Detail & Related papers (2024-03-06T18:47:32Z) - Mode-Aware Continual Learning for Conditional Generative Adversarial
Networks [27.28511396131235]
We introduce a new continual learning approach for conditional generative adversarial networks.
First, the generator produces samples of existing modes for subsequent replay.
The discriminator is then used to compute the mode similarity measure.
A label for the target mode is generated and given as a weighted average of the labels within this set.
arXiv Detail & Related papers (2023-05-19T03:00:31Z) - Reduce, Reuse, Recycle: Compositional Generation with Energy-Based
Diffusion Models and MCMC [106.06185677214353]
diffusion models have quickly become the prevailing approach to generative modeling in many domains.
We propose an energy-based parameterization of diffusion models which enables the use of new compositional operators.
We find these samplers lead to notable improvements in compositional generation across a wide set of problems.
arXiv Detail & Related papers (2023-02-22T18:48:46Z) - on the effectiveness of generative adversarial network on anomaly
detection [1.6244541005112747]
GANs rely on the rich contextual information of these models to identify the actual training distribution.
We suggest a new unsupervised model based on GANs --a combination of an autoencoder and a GAN.
A new scoring function was introduced to target anomalies where a linear combination of the internal representation of the discriminator and the generator's visual representation, plus the encoded representation of the autoencoder, come together to define the proposed anomaly score.
arXiv Detail & Related papers (2021-12-31T16:35:47Z) - Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial
Networks [3.040775019394542]
We propose a new online non-exhaustive learning model, namely, Non-Exhaustive Gaussian Mixture Generative Adversarial Networks (NE-GM-GAN)
Our proposed model synthesizes latent representation over a deep generative model, such as GAN, for incremental detection of instances of emerging classes in the test data.
arXiv Detail & Related papers (2021-06-28T00:20:22Z) - Task-agnostic Continual Learning with Hybrid Probabilistic Models [75.01205414507243]
We propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification.
The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting.
We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.
arXiv Detail & Related papers (2021-06-24T05:19:26Z) - Demonstrating the Evolution of GANs through t-SNE [0.4588028371034407]
Evolutionary algorithms, such as COEGAN, were recently proposed as a solution to improve the GAN training.
In this work, we propose an evaluation method based on t-distributed Neighbour Embedding (t-SNE) to assess the progress of GANs.
A metric based on the resulting t-SNE maps and the Jaccard index is proposed to represent the model quality.
arXiv Detail & Related papers (2021-01-31T20:07:08Z) - Understanding Classifier Mistakes with Generative Models [88.20470690631372]
Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle.
In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize.
Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
arXiv Detail & Related papers (2020-10-05T22:13:21Z) - GANs with Variational Entropy Regularizers: Applications in Mitigating
the Mode-Collapse Issue [95.23775347605923]
Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples.
GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution.
We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
arXiv Detail & Related papers (2020-09-24T19:34:37Z) - Unsupervised Controllable Generation with Self-Training [90.04287577605723]
controllable generation with GANs remains a challenging research problem.
We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training.
Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
arXiv Detail & Related papers (2020-07-17T21:50:35Z) - Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders [51.691585766702744]
We propose a variant of Adversarial Autoencoder which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction.
We put forward an alternative measure of anomaly score to replace the reconstruction-based metric.
Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.
arXiv Detail & Related papers (2020-03-24T08:26:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.