论文标题
我们可以使用强化学习学习图形模型推断的启发式方法吗？
Can We Learn Heuristics For Graphical Model Inference Using Reinforcement Learning?
论文作者
论文摘要
组合优化经常用于计算机视觉。例如，在语义分割，人姿势估计和动作识别等应用中，制定了程序以求解条件随机字段（CRF）的推断，以产生与图像的视觉特征一致的结构化输出。但是，解决CRF的推断通常是棘手的，近似方法在计算上是要求的，并且仅限于一元，成对和手工制作的高阶电位的形式。在本文中，我们表明我们可以使用强化学习来学习程序启发式方法，即政策，以解决更高级CRF的推论，以解决语义细分的任务。我们的方法有效地解决了推理任务，而无需对电势形式施加任何约束。我们在Pascal VOC和MOTS数据集上显示了令人信服的结果。
Combinatorial optimization is frequently used in computer vision. For instance, in applications like semantic segmentation, human pose estimation and action recognition, programs are formulated for solving inference in Conditional Random Fields (CRFs) to produce a structured output that is consistent with visual features of the image. However, solving inference in CRFs is in general intractable, and approximation methods are computationally demanding and limited to unary, pairwise and hand-crafted forms of higher order potentials. In this paper, we show that we can learn program heuristics, i.e., policies, for solving inference in higher order CRFs for the task of semantic segmentation, using reinforcement learning. Our method solves inference tasks efficiently without imposing any constraints on the form of the potentials. We show compelling results on the Pascal VOC and MOTS datasets.
