Inductive Biases for Object-Centric Representations of Complex Textures

04/18/2022
by   Samuele Papa, et al.
0

Understanding which inductive biases could be useful for the unsupervised learning of object-centric representations of natural scenes is challenging. Here, we use neural style transfer to generate datasets where objects have complex textures while still retaining ground-truth annotations. We find that, when a model effectively balances the importance of shape and appearance in the training objective, it can achieve better separation of the objects and learn more useful object representations.

READ FULL TEXT

page 1

page 4

page 13

page 18

page 19

page 21

page 22

research
07/01/2021

Generalization and Robustness Implications in Object-Centric Learning

The idea behind object-centric representation learning is that natural s...
research
07/13/2020

Reconstruction Bottlenecks in Object-Centric Generative Models

A range of methods with suitable inductive biases exist to learn interpr...
research
12/10/2022

Relate to Predict: Towards Task-Independent Knowledge Representations for Reinforcement Learning

Reinforcement Learning (RL) can enable agents to learn complex tasks. Ho...
research
06/12/2020

Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences

Perceiving the world in terms of objects is a crucial prerequisite for r...
research
05/23/2023

Provably Learning Object-Centric Representations

Learning structured representations of the visual world in terms of obje...
research
12/15/2021

Object Pursuit: Building a Space of Objects via Discriminative Weight Generation

We propose a framework to continuously learn object-centric representati...
research
03/11/2022

Towards Self-Supervised Learning of Global and Object-Centric Representations

Self-supervision allows learning meaningful representations of natural i...

Please sign up or login with your details

Forgot password? Click here to reset