Improving Out-of-Distribution Robustness of Classifiers via Generative
Interpolation
- URL: http://arxiv.org/abs/2307.12219v1
- Date: Sun, 23 Jul 2023 03:53:53 GMT
- Title: Improving Out-of-Distribution Robustness of Classifiers via Generative
Interpolation
- Authors: Haoyue Bai, Ceyuan Yang, Yinghao Xu, S.-H. Gary Chan, Bolei Zhou
- Abstract summary: Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data.
However, their performance deteriorates significantly when handling out-of-distribution (OoD) data.
We develop a simple yet effective method called Generative Interpolation to fuse generative models trained from multiple domains for synthesizing diverse OoD samples.
- Score: 56.620403243640396
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep neural networks achieve superior performance for learning from
independent and identically distributed (i.i.d.) data. However, their
performance deteriorates significantly when handling out-of-distribution (OoD)
data, where the training and test are drawn from different distributions. In
this paper, we explore utilizing the generative models as a data augmentation
source for improving out-of-distribution robustness of neural classifiers.
Specifically, we develop a simple yet effective method called Generative
Interpolation to fuse generative models trained from multiple domains for
synthesizing diverse OoD samples. Training a generative model directly on the
source domains tends to suffer from mode collapse and sometimes amplifies the
data bias. Instead, we first train a StyleGAN model on one source domain and
then fine-tune it on the other domains, resulting in many correlated generators
where their model parameters have the same initialization thus are aligned. We
then linearly interpolate the model parameters of the generators to spawn new
sets of generators. Such interpolated generators are used as an extra data
augmentation source to train the classifiers. The interpolation coefficients
can flexibly control the augmentation direction and strength. In addition, a
style-mixing mechanism is applied to further improve the diversity of the
generated OoD samples. Our experiments show that the proposed method explicitly
increases the diversity of training domains and achieves consistent
improvements over baselines across datasets and multiple different distribution
shifts.
Related papers
- First-Order Manifold Data Augmentation for Regression Learning [4.910937238451485]
We introduce FOMA: a new data-driven domain-independent data augmentation method.
We evaluate FOMA on in-distribution generalization and out-of-distribution benchmarks, and we show that it improves the generalization of several neural architectures.
arXiv Detail & Related papers (2024-06-16T12:35:05Z) - BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion [56.9358325168226]
We propose a Bagging deep learning training algorithm based on Efficient Neural network Diffusion (BEND)
Our approach is simple but effective, first using multiple trained model weights and biases as inputs to train autoencoder and latent diffusion model.
Our proposed BEND algorithm can consistently outperform the mean and median accuracies of both the original trained model and the diffused model.
arXiv Detail & Related papers (2024-03-23T08:40:38Z) - Distribution-Aware Data Expansion with Diffusion Models [55.979857976023695]
We propose DistDiff, a training-free data expansion framework based on the distribution-aware diffusion model.
DistDiff consistently enhances accuracy across a diverse range of datasets compared to models trained solely on original data.
arXiv Detail & Related papers (2024-03-11T14:07:53Z) - Diffusion-Model-Assisted Supervised Learning of Generative Models for
Density Estimation [10.793646707711442]
We present a framework for training generative models for density estimation.
We use the score-based diffusion model to generate labeled data.
Once the labeled data are generated, we can train a simple fully connected neural network to learn the generative model in the supervised manner.
arXiv Detail & Related papers (2023-10-22T23:56:19Z) - Phoenix: A Federated Generative Diffusion Model [6.09170287691728]
Training generative models on large centralized datasets can pose challenges in terms of data privacy, security, and accessibility.
This paper proposes a novel method for training a Denoising Diffusion Probabilistic Model (DDPM) across multiple data sources using Federated Learning (FL) techniques.
arXiv Detail & Related papers (2023-06-07T01:43:09Z) - Diff-Instruct: A Universal Approach for Transferring Knowledge From
Pre-trained Diffusion Models [77.83923746319498]
We propose a framework called Diff-Instruct to instruct the training of arbitrary generative models.
We show that Diff-Instruct results in state-of-the-art single-step diffusion-based models.
Experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models.
arXiv Detail & Related papers (2023-05-29T04:22:57Z) - 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) - Effective Dynamics of Generative Adversarial Networks [16.51305515824504]
Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples.
One major form of training failure, known as mode collapse, involves the generator failing to reproduce the full diversity of modes in the target probability distribution.
We present an effective model of GAN training, which captures the learning dynamics by replacing the generator neural network with a collection of particles in the output space.
arXiv Detail & Related papers (2022-12-08T22:04:01Z) - Self-Conditioned Generative Adversarial Networks for Image Editing [61.50205580051405]
Generative Adversarial Networks (GANs) are susceptible to bias, learned from either the unbalanced data, or through mode collapse.
We argue that this bias is responsible not only for fairness concerns, but that it plays a key role in the collapse of latent-traversal editing methods when deviating away from the distribution's core.
arXiv Detail & Related papers (2022-02-08T18:08:24Z) - 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)
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.