用少量样本学习新概念，模型能推断物体物理参数分布
Bayesian Inverse Graphics for Few-Shot Concept Learning
- 基于贝叶斯逆图形框架，从1张图推断物体物理参数后验分布
- 在少样本分类与姿态估计任务中超越纯神经网络方法
- 支持光照、背景变化下的泛化，且具备不确定性感知能力
人类仅需一个例子就能概括出新概念，而当前计算机视觉模型通常需要大量训练数据。本文提出一种基于贝叶斯感知的生成式逆图形模型，仅用极少量数据即可学习物体原型的概率程序。该模型通过基础形状的生成逆图形结构，从一张或多张图像中推断出物理上一致的参数后验分布，并可用于少样本分类和姿态估计等下游任务。模型利用可微分渲染器优化全局场景参数，结合马尔可夫链蒙特卡洛（MCMC）采样物体参数后验分布，并采用神经网络实现似然函数。实验表明，该模型在少样本分类上优于现有纯神经网络方法，且对光照、背景及分布外形状具有强泛化能力。模型设计上具备不确定性感知能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。