Unsupervised Object Keypoint Learning using Local Spatial Predictability

11/25/2020
by   Anand Gopalakrishnan, et al.
1

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.

READ FULL TEXT

page 2

page 3

page 6

page 7

page 16

page 17

page 18

page 19

research
11/04/2021

Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies

Salient object detection plays an important role in many downstream task...
research
06/11/2014

The Secrets of Salient Object Segmentation

In this paper we provide an extensive evaluation of fixation prediction ...
research
09/30/2022

An information-theoretic approach to unsupervised keypoint representation learning

Extracting informative representations from videos is fundamental for th...
research
01/19/2021

Salient Object Detection via Integrity Learning

Albeit current salient object detection (SOD) works have achieved fantas...
research
11/09/2015

Exploiting Egocentric Object Prior for 3D Saliency Detection

On a minute-to-minute basis people undergo numerous fluid interactions w...
research
04/22/2021

Motion Representations for Articulated Animation

We propose novel motion representations for animating articulated object...
research
05/04/2020

VisualEchoes: Spatial Image Representation Learning through Echolocation

Several animal species (e.g., bats, dolphins, and whales) and even visua...

Please sign up or login with your details

Forgot password? Click here to reset