论文标题
使用本地空间可预测性，无监督的对象关键点学习
Unsupervised Object Keypoint Learning using Local Spatial Predictability
论文作者
论文摘要
我们提出了Consakey，这是一种基于对象关键的表示表示学习的新方法。它利用空间邻域的本地图像区域的可预测性来识别与对象零件相对应的显着区域，然后将其转换为关键点。与先前的方法不同，它利用可预测性发现对象关键点，这是对象的内在属性。这样可以确保它不会过分偏置关键点，而要专注于不是对物体所独有的特征，例如运动，形状，颜色等。我们在atari上演示了通py在atari上的功效，其中它学习了与最显着的对象零件相对应的关键点，并且对某些视觉干扰物是可靠的。此外，在ATARI域中的下游RL任务上，我们演示了配备我们关键点的代理如何优于使用竞争替代方案的代理人，即使在具有动人的背景或分散对象的具有挑战性的环境中。
We propose PermaKey, a novel approach to representation learning based on object keypoints. It leverages the predictability of local image regions from spatial neighborhoods to identify salient regions that correspond to object parts, which are then converted to keypoints. Unlike prior approaches, it utilizes predictability to discover object keypoints, an intrinsic property of objects. This ensures that it does not overly bias keypoints to focus on characteristics that are not unique to objects, such as movement, shape, colour etc. We demonstrate the efficacy of PermaKey on Atari where it learns keypoints corresponding to the most salient object parts and is robust to certain visual distractors. Further, on downstream RL tasks in the Atari domain we demonstrate how agents equipped with our keypoints outperform those using competing alternatives, even on challenging environments with moving backgrounds or distractor objects.
