Related papers: Multi-Attribute Balanced Sampling for Disentangled GAN Controls

Multi-Attribute Balanced Sampling for Disentangled GAN Controls

URL: http://arxiv.org/abs/2111.00909v1
Date: Thu, 28 Oct 2021 08:44:13 GMT
Title: Multi-Attribute Balanced Sampling for Disentangled GAN Controls
Authors: Perla Doubinsky (CEDRIC - VERTIGO, CNAM), Nicolas Audebert (CEDRIC - VERTIGO, CNAM), Michel Crucianu (CEDRIC - VERTIGO, CNAM), Herv\'e Le Borgne (LIST)
Abstract summary: Various controls over the generated data can be extracted from the latent space of a pre-trained GAN. We show that this approach outperforms state-of-the-art classifier-based methods while avoiding the need for disentanglement-enforcing post-processing.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered controls allow to vary semantic attributes in the generated images but usually lead to entangled edits that affect multiple attributes at the same time. Supervised approaches typically sample and annotate a collection of latent codes, then train classifiers in the latent space to identify the controls. Since the data generated by GANs reflects the biases of the original dataset, so do the resulting semantic controls. We propose to address disentanglement by subsampling the generated data to remove over-represented co-occuring attributes thus balancing the semantics of the dataset before training the classifiers. We demonstrate the effectiveness of this approach by extracting disentangled linear directions for face manipulation on two popular GAN architectures, PGGAN and StyleGAN, and two datasets, CelebAHQ and FFHQ. We show that this approach outperforms state-of-the-art classifier-based methods while avoiding the need for disentanglement-enforcing post-processing.

Related papers

DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control [68.14798033899955]
Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content. However, are they usable as large-scale data generators, e.g., to improve tasks in the perception stack, like semantic segmentation? We investigate this question in the context of autonomous driving, and answer it with a resounding "yes"
arXiv Detail & Related papers (2023-12-05T18:34:12Z)
Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning [11.245813423781415]
We devise novel data-driven supervision for data by introducing a characteristic -- scale -- as data labels. Scales serve as labels attached to transformed representations, thus offering ample labeled data for neural network training. This paper further proposes a scale learning-based anomaly detection method.
arXiv Detail & Related papers (2023-05-25T14:48:00Z)
Wasserstein Loss for Semantic Editing in the Latent Space of GANs [0.0]
Different methods propose to learn edits in latent space corresponding to semantic attributes. Most supervised methods rely on the guidance of classifiers to produce such edits. We propose an alternative formulation based on the Wasserstein loss that avoids such problems.
arXiv Detail & Related papers (2023-03-22T08:15:27Z)
Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning [125.99533416395765]
We argue that the performance of the final classifier depends on the data separation present in the latent space and visual separation present in the projection. We demonstrate our results by the classification of five real-world challenging image datasets of human intestinal parasites with only 1% supervised samples.
arXiv Detail & Related papers (2023-02-06T10:01:38Z)
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
arXiv Detail & Related papers (2022-11-12T09:21:49Z)
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
arXiv Detail & Related papers (2022-10-11T08:24:50Z)
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)
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)

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