Related papers: Generator Born from Classifier

Generator Born from Classifier

URL: http://arxiv.org/abs/2312.02470v1
Date: Tue, 5 Dec 2023 03:41:17 GMT
Title: Generator Born from Classifier
Authors: Runpeng Yu, Xinchao Wang
Abstract summary: We aim to reconstruct an image generator, without relying on any data samples. We propose a novel learning paradigm, in which the generator is trained to ensure that the convergence conditions of the network parameters are satisfied.
Score: 66.56001246096002
License: http://creativecommons.org/licenses/by/4.0/
Abstract: In this paper, we make a bold attempt toward an ambitious task: given a pre-trained classifier, we aim to reconstruct an image generator, without relying on any data samples. From a black-box perspective, this challenge seems intractable, since it inevitably involves identifying the inverse function for a classifier, which is, by nature, an information extraction process. As such, we resort to leveraging the knowledge encapsulated within the parameters of the neural network. Grounded on the theory of Maximum-Margin Bias of gradient descent, we propose a novel learning paradigm, in which the generator is trained to ensure that the convergence conditions of the network parameters are satisfied over the generated distribution of the samples. Empirical validation from various image generation tasks substantiates the efficacy of our strategy.

Related papers

Plug-and-Play Controllable Generation for Discrete Masked Models [27.416952690340903]
This article makes discrete masked models for the generative modeling of discrete data controllable. We propose a novel plug-and-play framework based on importance sampling that bypasses the need for training a conditional score. Our framework is agnostic to the choice of control criteria, requires no gradient information, and is well-suited for tasks such as posterior sampling, Bayesian inverse problems, and constrained generation.
arXiv Detail & Related papers (2024-10-03T02:00:40Z)
Time-series Generation by Contrastive Imitation [87.51882102248395]
We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
arXiv Detail & Related papers (2023-11-02T16:45:25Z)
Dual Student Networks for Data-Free Model Stealing [79.67498803845059]
Two main challenges are estimating gradients of the target model without access to its parameters, and generating a diverse set of training samples. We propose a Dual Student method where two students are symmetrically trained in order to provide the generator a criterion to generate samples that the two students disagree on. We show that our new optimization framework provides more accurate gradient estimation of the target model and better accuracies on benchmark classification datasets.
arXiv Detail & Related papers (2023-09-18T18:11:31Z)
Efficient Failure Pattern Identification of Predictive Algorithms [15.02620042972929]
We propose a human-machine collaborative framework that consists of a team of human annotators and a sequential recommendation algorithm. The results empirically demonstrate the competitive performance of our framework on multiple datasets at various signal-to-noise ratios.
arXiv Detail & Related papers (2023-06-01T14:54:42Z)
Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks [0.0]
Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Here we quantitatively test this approach by applying it to a prototypical process on a lattice. Importantly, the discreteness of the model is retained despite the noise.
arXiv Detail & Related papers (2023-05-25T10:41:02Z)
StyleGenes: Discrete and Efficient Latent Distributions for GANs [149.0290830305808]
We propose a discrete latent distribution for Generative Adversarial Networks (GANs) Instead of drawing latent vectors from a continuous prior, we sample from a finite set of learnable latents. We take inspiration from the encoding of information in biological organisms.
arXiv Detail & Related papers (2023-04-30T23:28:46Z)
Toward Certified Robustness Against Real-World Distribution Shifts [65.66374339500025]
We train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations. We propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement.
arXiv Detail & Related papers (2022-06-08T04:09:13Z)
Conditional Variational Autoencoder for Learned Image Reconstruction [5.487951901731039]
We develop a novel framework that approximates the posterior distribution of the unknown image at each query observation. It handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets.
arXiv Detail & Related papers (2021-10-22T10:02:48Z)
Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
arXiv Detail & Related papers (2020-06-22T15:07:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.