PCAAE: Principal Component Analysis Autoencoder for organising the latent space of generative networks

• URL: http://arxiv.org/abs/2006.07827v1
• Date: Sun, 14 Jun 2020 07:40:45 GMT
• Title: PCAAE: Principal Component Analysis Autoencoder for organising the latent space of generative networks
• Authors: Chi-Hieu Pham and Sa\"id Ladjal and Alasdair Newson
• Abstract summary: We propose a novel autoencoder whose latent space verifies two properties. The components of the latent space are statistically independent. We show results on both synthetic examples of shapes and on a state-of-the-art GAN.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoencoders and generative models produce some of the most spectacular deep learning results to date. However, understanding and controlling the latent space of these models presents a considerable challenge. Drawing inspiration from principal component analysis and autoencoder, we propose the Principal Component Analysis Autoencoder (PCAAE). This is a novel autoencoder whose latent space verifies two properties. Firstly, the dimensions are organised in decreasing importance with respect to the data at hand. Secondly, the components of the latent space are statistically independent. We achieve this by progressively increasing the latent space during training, and with a covariance loss applied to the latent codes. The resulting autoencoder produces a latent space which separates the intrinsic attributes of the data into different components of the latent space, in a completely unsupervised manner. We also describe an extension of our approach to the case of powerful, pre-trained GANs. We show results on both synthetic examples of shapes and on a state-of-the-art GAN. For example, we are able to separate the color shade scale of hair and skin, pose of faces and the gender in the CelebA, without accessing any labels. We compare the PCAAE with other state-of-the-art approaches, in particular with respect to the ability to disentangle attributes in the latent space. We hope that this approach will contribute to better understanding of the intrinsic latent spaces of powerful deep generative models.

Related papers

• GraCo: Granularity-Controllable Interactive Segmentation [52.9695642626127]
  Granularity-Controllable Interactive (GraCo) is a novel approach that allows precise control of prediction granularity by introducing additional parameters to input. GraCo exploits the semantic property of the pre-trained IS model to automatically generate abundant mask-granularity pairs. Experiments on intricate scenarios at object and part levels demonstrate that our GraCo has significant advantages over previous methods.
  arXiv  Detail & Related papers  (2024-05-01T15:50:16Z)
• N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields [112.02885337510716]
  Nested Neural Feature Fields (N2F2) is a novel approach that employs hierarchical supervision to learn a single feature field. We leverage a 2D class-agnostic segmentation model to provide semantically meaningful pixel groupings at arbitrary scales in the image space. Our approach outperforms the state-of-the-art feature field distillation methods on tasks such as open-vocabulary 3D segmentation and localization.
  arXiv  Detail & Related papers  (2024-03-16T18:50:44Z)
• A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing [4.8201607588546]
  We propose an auto-encoder which re-organizes the latent space of StyleGAN, so that each attribute which we wish to edit corresponds to an axis of the new latent space. We show that our approach has greater disentanglement than competing methods, while maintaining fidelity to the original image with respect to identity.
  arXiv  Detail & Related papers  (2023-12-13T16:18:45Z)
• SC2GAN: Rethinking Entanglement by Self-correcting Correlated GAN Space [16.040942072859075]
  Gene Networks that achieve following editing directions for one attribute could result in entangled changes with other attributes. We propose a novel framework SC$2$GAN disentanglement by re-projecting low-density latent code samples in the original latent space.
  arXiv  Detail & Related papers  (2023-10-10T14:42:32Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Spatial Steerability of GANs via Self-Supervision from Discriminator [123.27117057804732]
  We propose a self-supervised approach to improve the spatial steerability of GANs without searching for steerable directions in the latent space. Specifically, we design randomly sampled Gaussian heatmaps to be encoded into the intermediate layers of generative models as spatial inductive bias. During inference, users can interact with the spatial heatmaps in an intuitive manner, enabling them to edit the output image by adjusting the scene layout, moving, or removing objects.
  arXiv  Detail & Related papers  (2023-01-20T07:36:29Z)
• Disentangling Variational Autoencoders [0.0]
  A variational autoencoder (VAE) projects an input set of high-dimensional data to a lower-dimensional, latent space. We implement three different VAE models from the literature and train them on a dataset of 60,000 images of hand-written digits. We investigate the trade-offs between the quality of the reconstruction of the decoded images and the level of disentanglement of the latent space.
  arXiv  Detail & Related papers  (2022-11-14T19:22:41Z)
• Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction [27.020835928724775]
  This work proposes a new computational framework for learning an explicit generative model for real-world datasets. In particular, we propose to learn em a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space. Our experiments on many benchmark imagery datasets demonstrate tremendous potential of this new closed-loop formulation.
  arXiv  Detail & Related papers  (2021-11-12T10:06:08Z)
• Is Disentanglement enough? On Latent Representations for Controllable Music Generation [78.8942067357231]
  In the absence of a strong generative decoder, disentanglement does not necessarily imply controllability. The structure of the latent space with respect to the VAE-decoder plays an important role in boosting the ability of a generative model to manipulate different attributes.
  arXiv  Detail & Related papers  (2021-08-01T18:37:43Z)
• IntroVAC: Introspective Variational Classifiers for Learning Interpretable Latent Subspaces [6.574517227976925]
  IntroVAC learns interpretable latent subspaces by exploiting information from an additional label. We show that IntroVAC is able to learn meaningful directions in the latent space enabling fine manipulation of image attributes.
  arXiv  Detail & Related papers  (2020-08-03T10:21:41Z)

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.