Diverse Image Generation via Self-Conditioned GANs
- URL: http://arxiv.org/abs/2006.10728v2
- Date: Thu, 10 Feb 2022 01:57:02 GMT
- Title: Diverse Image Generation via Self-Conditioned GANs
- Authors: Steven Liu, Tongzhou Wang, David Bau, Jun-Yan Zhu, Antonio Torralba
- Abstract summary: We train a class-conditional GAN model without using manually annotated class labels.
Instead, our model is conditional on labels automatically derived from clustering in the discriminator's feature space.
Our clustering step automatically discovers diverse modes, and explicitly requires the generator to cover them.
- Score: 56.91974064348137
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We introduce a simple but effective unsupervised method for generating
realistic and diverse images. We train a class-conditional GAN model without
using manually annotated class labels. Instead, our model is conditional on
labels automatically derived from clustering in the discriminator's feature
space. Our clustering step automatically discovers diverse modes, and
explicitly requires the generator to cover them. Experiments on standard mode
collapse benchmarks show that our method outperforms several competing methods
when addressing mode collapse. Our method also performs well on large-scale
datasets such as ImageNet and Places365, improving both image diversity and
standard quality metrics, compared to previous methods.
Related papers
- Gradient-Free Classifier Guidance for Diffusion Model Sampling [4.450496470631169]
Gradient-free Guidance (GFCG) method consistently improves class prediction accuracy.
For ImageNet 512$times$512, we achieve a record $FD_textDINOv2$ 23.09, while simultaneously attaining a higher classification Precision (94.3%) compared to ATG (90.2%)
arXiv Detail & Related papers (2024-11-23T00:22:21Z) - Self-Guided Diffusion Models [53.825634944114285]
We propose a framework for self-guided diffusion models.
Our method provides guidance signals at various image granularities.
Our experiments on single-label and multi-label image datasets demonstrate that self-labeled guidance always outperforms diffusion models without guidance.
arXiv Detail & Related papers (2022-10-12T17:57:58Z) - A Generalist Framework for Panoptic Segmentation of Images and Videos [61.61453194912186]
We formulate panoptic segmentation as a discrete data generation problem, without relying on inductive bias of the task.
A diffusion model is proposed to model panoptic masks, with a simple architecture and generic loss function.
Our method is capable of modeling video (in a streaming setting) and thereby learns to track object instances automatically.
arXiv Detail & Related papers (2022-10-12T16:18:25Z) - Spatially Multi-conditional Image Generation [80.04130168156792]
We propose a novel neural architecture to address the problem of multi-conditional image generation.
The proposed method uses a transformer-like architecture operating pixel-wise, which receives the available labels as input tokens.
Our experiments on three benchmark datasets demonstrate the clear superiority of our method over the state-of-the-art and the compared baselines.
arXiv Detail & Related papers (2022-03-25T17:57:13Z) - Out-of-Distribution Detection without Class Labels [29.606812876314386]
Anomaly detection methods identify samples that deviate from the normal behavior of the dataset.
Current methods struggle when faced with training data consisting of multiple classes but no labels.
We first cluster images using self-supervised methods and obtain a cluster label for every image.
We finetune pretrained features on the task of classifying images by their cluster labels.
arXiv Detail & Related papers (2021-12-14T18:58:32Z) - Diverse Semantic Image Synthesis via Probability Distribution Modeling [103.88931623488088]
We propose a novel diverse semantic image synthesis framework.
Our method can achieve superior diversity and comparable quality compared to state-of-the-art methods.
arXiv Detail & Related papers (2021-03-11T18:59:25Z) - Unsupervised Image Segmentation using Mutual Mean-Teaching [12.784209596867495]
We propose an unsupervised image segmentation model based on the Mutual Mean-Teaching (MMT) framework to produce more stable results.
Experimental results demonstrate that the proposed model is able to segment various types of images and achieves better performance than the existing methods.
arXiv Detail & Related papers (2020-12-16T13:13:34Z) - Efficient Full Image Interactive Segmentation by Leveraging Within-image
Appearance Similarity [39.17599924322882]
We propose a new approach to interactive full-image semantic segmentation.
We leverage a key observation: propagation from labeled to unlabeled pixels does not necessarily require class-specific knowledge.
We build on this observation and propose an approach capable of jointly propagating pixel labels from multiple classes.
arXiv Detail & Related papers (2020-07-16T08:21:59Z) - Enhancing Few-Shot Image Classification with Unlabelled Examples [18.03136114355549]
We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance.
Our approach combines a regularized neural adaptive feature extractor to achieve improved test-time classification accuracy using unlabelled data.
arXiv Detail & Related papers (2020-06-17T05:42:47Z) - Evaluating the Disentanglement of Deep Generative Models through
Manifold Topology [66.06153115971732]
We present a method for quantifying disentanglement that only uses the generative model.
We empirically evaluate several state-of-the-art models across multiple datasets.
arXiv Detail & Related papers (2020-06-05T20:54:11Z)
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.