Unsupervised Program Synthesis for Images By Sampling Without Replacement

2020-01-27 · Chenghui Zhou, Chun-Liang Li, Barnabas Poczos

Program synthesis has emerged as a successful approach to the image parsing task. Most prior works rely on a two-step scheme involving supervised pretraining of a Seq2Seq model with synthetic programs followed by reinforcement learning (RL) for fine-tuning with real reference images. Fully unsupervised approaches promise to train the model directly on the target images without requiring curated pretraining datasets. However, they struggle with the inherent sparsity of meaningful programs in the search space. In this paper, we present the first unsupervised algorithm capable of parsing constructive solid geometry (CSG) images into context-free grammar (CFG) without pretraining via non-differentiable renderer. To tackle the \emph{non-Markovian} sparse reward problem, we combine three key ingredients -- (i) a grammar-encoded tree LSTM ensuring program validity (ii) entropy regularization and (iii) sampling without replacement from the CFG syntax tree. Empirically, our algorithm recovers meaningful programs in large search spaces (up to $3.8 \times 10^{28}$). Further, even though our approach is fully unsupervised, it generalizes better than supervised methods on the synthetic 2D CSG dataset. On the 2D computer aided design (CAD) dataset, our approach significantly outperforms the supervised pretrained model and is competitive to the refined model.

📄 PDF Abstract BibTeX arXiv:2001.10119

Code (0)

등록된 구현이 없습니다.

Tasks

Program Synthesis Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Unsupervised Learning by Program Synthesis

2015-12-01 · NeurIPS 2015 12 · Kevin Ellis, Armando Solar-Lezama, Josh Tenenbaum

We introduce an unsupervised learning algorithmthat combines probabilistic modeling with solver-based techniques for program synthesis.We apply our techniques to both a visual learning domain and a language learning prob…

Program Synthesis

Incremental Sampling Without Replacement for Sequence Models

2020-02-21 · ICML 2020 1 · Kensen Shi, David Bieber, Charles Sutton

Sampling is a fundamental technique, and sampling without replacement is often desirable when duplicate samples are not beneficial. Within machine learning, sampling is useful for generating diverse outputs from a traine…

Combinatorial Optimization Program Synthesis

DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis

2022-08-13 · Jingliang Li, Zhengda Lu, Yiqun Wang, Ying Wang 외

In recent years, supervised or unsupervised learning-based MVS methods achieved excellent performance compared with traditional methods. However, these methods only use the probability volume computed by cost volume regu…

Semi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study

2020-07-23 · Simón C. Smith, Subramanian Ramamoorthy

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a sys…

Clustering counterfactual Decision Making Model Predictive Control+1

Unbiased Image Synthesis via Manifold Guidance in Diffusion Models

2023-07-17 · Xingzhe Su, Daixi Jia, Fengge Wu, Junsuo Zhao 외

Diffusion Models are a potent class of generative models capable of producing high-quality images. However, they often inadvertently favor certain data attributes, undermining the diversity of generated images. This issu…

Diversity Image Generation