Self-Supervised Variational Auto-Encoders

• URL: http://arxiv.org/abs/2010.02014v2
• Date: Tue, 6 Oct 2020 08:20:15 GMT
• Title: Self-Supervised Variational Auto-Encoders
• Authors: Ioannis Gatopoulos and Jakub M. Tomczak
• Abstract summary: We present a novel class of generative models, called self-supervised Variational Auto-Encoder (selfVAE) This class of models allows to perform both conditional and unconditional sampling, while simplifying the objective function. We present performance of our approach on three benchmark image data (Cifar10, Imagenette64, and CelebA)
• Score: 10.482805367361818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Density estimation, compression and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models, called self-supervised Variational Auto-Encoder (selfVAE), that utilizes deterministic and discrete variational posteriors. This class of models allows to perform both conditional and unconditional sampling, while simplifying the objective function. First, we use a single self-supervised transformation as a latent variable, where a transformation is either downscaling or edge detection. Next, we consider a hierarchical architecture, i.e., multiple transformations, and we show its benefits compared to the VAE. The flexibility of selfVAE in data reconstruction finds a particularly interesting use case in data compression tasks, where we can trade-off memory for better data quality, and vice-versa. We present performance of our approach on three benchmark image data (Cifar10, Imagenette64, and CelebA).

Related papers

• Variational Autoencoding Neural Operators [17.812064311297117]
  Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. We present Variational Autoencoding Neural Operators (VANO), a general strategy for making a large class of operator learning architectures act as variational autoencoders.
  arXiv  Detail & Related papers  (2023-02-20T22:34:43Z)
• Unifying Flow, Stereo and Depth Estimation [121.54066319299261]
  We present a unified formulation and model for three motion and 3D perception tasks. We formulate all three tasks as a unified dense correspondence matching problem. Our model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks.
  arXiv  Detail & Related papers  (2022-11-10T18:59:54Z)
• Patch Similarity Aware Data-Free Quantization for Vision Transformers [2.954890575035673]
  We propose PSAQ-ViT, a Patch Similarity Aware data-free Quantization framework for Vision Transformers. We analyze the self-attention module's properties and reveal a general difference (patch similarity) in its processing of Gaussian noise and real images. Experiments and ablation studies are conducted on various benchmarks to validate the effectiveness of PSAQ-ViT.
  arXiv  Detail & Related papers  (2022-03-04T11:47:20Z)
• ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond [76.35955924137986]
  We propose a Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context. We obtain the state-of-the-art classification performance, i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the best 91.2% Top-1 accuracy on ImageNet real validation set.
  arXiv  Detail & Related papers  (2022-02-21T10:40:05Z)
• Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning [19.854565192491123]
  We present a novel multi-modal data augmentation approach named Dizygotic Conditional Variational AutoEncoder (DCVAE) DCVAE conducts feature synthesis via pairing two Conditional Variational AutoEncoders (CVAEs) with the same seed but different modality conditions in a dizygotic symbiosis manner. The generated features of two CVAEs are adaptively combined to yield the final feature, which can be converted back into its paired conditions.
  arXiv  Detail & Related papers  (2021-06-28T08:29:55Z)
• Discrete Auto-regressive Variational Attention Models for Text Modeling [53.38382932162732]
  Variational autoencoders (VAEs) have been widely applied for text modeling. They are troubled by two challenges: information underrepresentation and posterior collapse. We propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges.
  arXiv  Detail & Related papers  (2021-06-16T06:36:26Z)
• Multi-Facet Clustering Variational Autoencoders [9.150555507030083]
  High-dimensional data, such as images, typically feature multiple interesting characteristics one could cluster over. We introduce Multi-Facet Clustering Variational Autoencoders (MFCVAE) MFCVAE learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end.
  arXiv  Detail & Related papers  (2021-06-09T17:36:38Z)
• Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model [58.17021225930069]
  We explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) We propose a more efficient EAT model, and design task-related heads to deal with different tasks more flexibly. Our approach achieves state-of-the-art results on the ImageNet classification task compared with recent vision transformer works.
  arXiv  Detail & Related papers  (2021-05-31T16:20:03Z)
• Consistency Regularization for Variational Auto-Encoders [14.423556966548544]
  Variational auto-encoders (VAEs) are a powerful approach to unsupervised learning. We propose a regularization method to enforce consistency in VAEs.
  arXiv  Detail & Related papers  (2021-05-31T10:26:32Z)
• IOT: Instance-wise Layer Reordering for Transformer Structures [173.39918590438245]
  We break the assumption of the fixed layer order in the Transformer and introduce instance-wise layer reordering into the model structure. Our method can also be applied to other architectures beyond Transformer.
  arXiv  Detail & Related papers  (2021-03-05T03:44:42Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)

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.