Unsupervised learning of object keypoints for perception and control

Conference item

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and reinforcement learning (RL). To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates. Our method learns from raw video frames in a fully unsupervised manner, by transporting learnt image features between video frames using a keypoint bottleneck. The discovered keypoints track objects and object parts across long time-horizons more accurately than recent similar methods. Furthermore, consistent long-term tracking enables two notable results in control domains -- (1) using the keypoint co-ordinates and corresponding image features as inputs enables highly sample-efficient reinforcement learning; (2) learning to explore by controlling keypoint locations drastically reduces the search space, enabling deep exploration (leading to states unreachable through random action exploration) without any extrinsic rewards.

Authors: Kulkarni, T; Gupta, A; Ionescu, C; Borgeaud, S; Reynolds, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Curran Associates
• Host title: Advances in Neural Information Processing Systems 32: 32nd Conference on Neural Information Processing Systems (NeurIPS 2019)
• Volume: 32
• Pages: 10692-10702
• Publication date: 2020-06-01
• Acceptance date: 2019-09-04
• Event title: Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
• Event location: Vancouver, Canada
• Event website: https://nips.cc/Conferences/2019
• Event start date: 2019-12-08
• Event end date: 2019-12-14
• ISSN: 1049-5258
• ISBN: 9781713807933
• Language: English
• Keywords: FFR