PatchVAE: Learning Local Latent Codes for Recognition

• URL: http://arxiv.org/abs/2004.03623v1
• Date: Tue, 7 Apr 2020 18:01:26 GMT
• Title: PatchVAE: Learning Local Latent Codes for Recognition
• Abstract summary: unsupervised representations learned by VAEs are significantly outperformed by those learned by supervised learning for recognition. Our hypothesis is that to learn useful representations for recognition the model needs to be encouraged to learn about repeating and consistent patterns in data. Our experiments demonstrate that representations learned by our method perform much better on the recognition tasks compared to those learned by vanilla VAEs.
• Score: 38.82903227239025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs). However, unsupervised representations learned by VAEs are significantly outperformed by those learned by supervised learning for recognition. Our hypothesis is that to learn useful representations for recognition the model needs to be encouraged to learn about repeating and consistent patterns in data. Drawing inspiration from the mid-level representation discovery work, we propose PatchVAE, that reasons about images at patch level. Our key contribution is a bottleneck formulation that encourages mid-level style representations in the VAE framework. Our experiments demonstrate that representations learned by our method perform much better on the recognition tasks compared to those learned by vanilla VAEs.

Related papers

• Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning [42.04086618646585]
  Self-supervised learning (SSL) have improved empirical performance by unleashing the power of unlabeled data for practical applications.<n>This paper develops a principled foundation of representation learning, which paves the path to a unified framework for understanding and analysis.
  arXiv  Detail & Related papers  (2026-01-28T01:08:24Z)
• FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection [25.015218537268115]
  We propose an innovative CLIP-based framework based on Forced prompt leArning (FA) to make full use of the In-Distribution (ID) knowledge.<n>FA is capable of achieving notable improvements in OOD detection, even when trained without any external auxiliary datasets.
  arXiv  Detail & Related papers  (2025-07-06T19:16:03Z)
• A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
  In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. We present a generative latent variable model for self-supervised learning. We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
  arXiv  Detail & Related papers  (2024-02-02T13:31:17Z)
• Improving VAE-based Representation Learning [26.47244578124654]
  We study what properties are required for good representations and how different VAE structure choices could affect the learned properties. We show that by using a decoder that prefers to learn local features, the remaining global features can be well captured by the latent.
  arXiv  Detail & Related papers  (2022-05-28T23:00:18Z)
• An Empirical Investigation of Representation Learning for Imitation [76.48784376425911]
  Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data. We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation.
  arXiv  Detail & Related papers  (2022-05-16T11:23:42Z)
• High Fidelity Visualization of What Your Self-Supervised Representation Knows About [22.982471878833362]
  In this work, we showcase the use of a conditional diffusion based generative model (RCDM) to visualize representations learned with self-supervised models. We demonstrate how this model's generation quality is on par with state-of-the-art generative models while being faithful to the representation used as conditioning.
  arXiv  Detail & Related papers  (2021-12-16T19:23:33Z)
• Co$^2$L: Contrastive Continual Learning [69.46643497220586]
  Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks. We propose a rehearsal-based continual learning algorithm that focuses on continually learning and maintaining transferable representations.
  arXiv  Detail & Related papers  (2021-06-28T06:14:38Z)
• Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge [59.87823082513752]
  This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We empirically study the relevance of various KBs to multiple tasks and benchmarks. The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.
  arXiv  Detail & Related papers  (2021-01-15T08:37:55Z)
• Guided Variational Autoencoder for Disentanglement Learning [79.02010588207416]
  We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. We design an unsupervised strategy and a supervised strategy in Guided-VAE and observe enhanced modeling and controlling capability over the vanilla VAE.
  arXiv  Detail & Related papers  (2020-04-02T20:49:15Z)

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.