Bayesian Inverse Graphics for Few-Shot Concept Learning
- URL: http://arxiv.org/abs/2409.08351v1
- Date: Thu, 12 Sep 2024 18:30:41 GMT
- Title: Bayesian Inverse Graphics for Few-Shot Concept Learning
- Authors: Octavio Arriaga, Jichen Guo, Rebecca Adam, Sebastian Houben, Frank Kirchner,
- Abstract summary: We present a Bayesian model of perception that learns using only minimal data.
We show how this representation can be used for downstream tasks such as few-shot classification and estimation.
- Score: 3.475273727432576
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Humans excel at building generalizations of new concepts from just one single example. Contrary to this, current computer vision models typically require large amount of training samples to achieve a comparable accuracy. In this work we present a Bayesian model of perception that learns using only minimal data, a prototypical probabilistic program of an object. Specifically, we propose a generative inverse graphics model of primitive shapes, to infer posterior distributions over physically consistent parameters from one or several images. We show how this representation can be used for downstream tasks such as few-shot classification and pose estimation. Our model outperforms existing few-shot neural-only classification algorithms and demonstrates generalization across varying lighting conditions, backgrounds, and out-of-distribution shapes. By design, our model is uncertainty-aware and uses our new differentiable renderer for optimizing global scene parameters through gradient descent, sampling posterior distributions over object parameters with Markov Chain Monte Carlo (MCMC), and using a neural based likelihood function.
Related papers
- Scaling and renormalization in high-dimensional regression [72.59731158970894]
This paper presents a succinct derivation of the training and generalization performance of a variety of high-dimensional ridge regression models.
We provide an introduction and review of recent results on these topics, aimed at readers with backgrounds in physics and deep learning.
arXiv Detail & Related papers (2024-05-01T15:59:00Z) - Happy People -- Image Synthesis as Black-Box Optimization Problem in the
Discrete Latent Space of Deep Generative Models [10.533348468499826]
We propose a novel image generative approach that optimize the generated sample with respect to a continuously quantifiable property.
Specifically, we propose to use tree-based ensemble models as mathematical programs over the discrete latent space of vector quantized VAEs.
arXiv Detail & Related papers (2023-06-11T13:58:36Z) - Bayesian Neural Network Inference via Implicit Models and the Posterior
Predictive Distribution [0.8122270502556371]
We propose a novel approach to perform approximate Bayesian inference in complex models such as Bayesian neural networks.
The approach is more scalable to large data than Markov Chain Monte Carlo.
We see this being useful in applications such as surrogate and physics-based models.
arXiv Detail & Related papers (2022-09-06T02:43:19Z) - RelPose: Predicting Probabilistic Relative Rotation for Single Objects
in the Wild [73.1276968007689]
We describe a data-driven method for inferring the camera viewpoints given multiple images of an arbitrary object.
We show that our approach outperforms state-of-the-art SfM and SLAM methods given sparse images on both seen and unseen categories.
arXiv Detail & Related papers (2022-08-11T17:59:59Z) - A new perspective on probabilistic image modeling [92.89846887298852]
We present a new probabilistic approach for image modeling capable of density estimation, sampling and tractable inference.
DCGMMs can be trained end-to-end by SGD from random initial conditions, much like CNNs.
We show that DCGMMs compare favorably to several recent PC and SPN models in terms of inference, classification and sampling.
arXiv Detail & Related papers (2022-03-21T14:53:57Z) - Probabilistic Tracking with Deep Factors [8.030212474745879]
We show how to use a deep feature encoding in conjunction with generative densities over the features in a factor-graph based, probabilistic tracking framework.
We present a likelihood model that combines a learned feature encoder with generative densities over them, both trained in a supervised manner.
arXiv Detail & Related papers (2021-12-02T21:31:51Z) - Exponentially Tilted Gaussian Prior for Variational Autoencoder [3.52359746858894]
Recent studies show that probabilistic generative models can perform poorly on this task.
We propose the exponentially tilted Gaussian prior distribution for the Variational Autoencoder (VAE)
We show that our model produces high quality image samples which are more crisp than that of a standard Gaussian VAE.
arXiv Detail & Related papers (2021-11-30T18:28:19Z) - Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
We take a two-step approach by first modeling the probability distribution and then sampling from that model.
We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
arXiv Detail & Related papers (2021-10-20T12:25:22Z) - Probabilistic Modeling for Human Mesh Recovery [73.11532990173441]
This paper focuses on the problem of 3D human reconstruction from 2D evidence.
We recast the problem as learning a mapping from the input to a distribution of plausible 3D poses.
arXiv Detail & Related papers (2021-08-26T17:55:11Z) - A Bayesian Perspective on Training Speed and Model Selection [51.15664724311443]
We show that a measure of a model's training speed can be used to estimate its marginal likelihood.
We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks.
Our results suggest a promising new direction towards explaining why neural networks trained with gradient descent are biased towards functions that generalize well.
arXiv Detail & Related papers (2020-10-27T17:56:14Z)
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.