2021/10/27 by Đ. Khuê Lê-Huu, Karteek Alahari, Lê-Huu, Đ. Khuê +1 · 7 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Algorithm #Approximate inference #Artificial intelligence #CRFS #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Conditional random field #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Mathematics #Generalization #Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mathematics #Optimization and Control (math.OC) #Segmentation #Stochastic Gradient Optimization Techniques #cs.CV #cs.LG #math.OC #stat.ML
paper · pdf · doi:10.48550/arxiv.2110.14759
published in arXiv (Cornell University) (Cornell University) · NeurIPS 2021. This version fixed some minor typos (constant factor 2 removed from bottom-right cell of Theorem 1's table, and from last row of Table 5)
openalex publication_date 2021/10/27 · openalex created_date 2022/07/25 · arxiv created 2022/09/07 · arxiv updated 2022/09/09 · openalex updated_date 2026/07/28
We introduce regularized Frank-Wolfe, a general and effective algorithm for inference and learning of dense conditional random fields (CRFs). The algorithm optimizes a nonconvex continuous relaxation of the CRF inference problem using vanilla Frank-Wolfe with approximate updates, which are equivalent to minimizing a regularized energy function. Our proposed method is a generalization of existing algorithms such as mean field or concave-convex procedure. This perspective not only offers a unified analysis of these algorithms, but also allows an easy way of exploring different variants that potentially yield better performance. We illustrate this in our empirical results on standard semantic segmentation datasets, where several instantiations of our regularized Frank-Wolfe outperform mean field inference, both as a standalone component and as an end-to-end trainable layer in a neural network. We also show that dense CRFs, coupled with our new algorithms, produce significant improvements over strong CNN baselines.