AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Unsupervised Learning of Object Keypoints for Perception and Control

Tejas D Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman, Volodymyr Mnih

NeurIPS 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 106 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use feature transport between frames with a keypoint bottleneckTransporter · Atari ALE and Manipulator trackinglong-term keypoint trackingImproved
Use Transporter keypoints and corresponding image features as policy inputsKeyQN · Atari ALE, 5 gamesmean game scoreImproved
Explore by controlling keypoint coordinates with temporally extended optionsTransporter keypoint options · Montezuma's Revenge, Ms. Pac-Man, Seaquestepisodic returnImproved
Transport learned features rather than pixels (ablation)Transporter · Manipulator tabletop toyspixel reconstruction errorImproved
Compare Transporter with Zhang et al. on Ms. Pac-Man trackingTransporter · Ms. Pac-Manlong-term keypoint trackingMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy