DeepAI AI Chat
Log In Sign Up

Boosting Object Representation Learning via Motion and Object Continuity

by   Quentin Delfosse, et al.

Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they may produce suboptimal object encodings for downstream tasks. To overcome this, we propose to exploit object motion and continuity, i.e., objects do not pop in and out of existence. This is accomplished through two mechanisms: (i) providing priors on the location of objects through integration of optical flow, and (ii) a contrastive object continuity loss across consecutive image frames. Rather than developing an explicit deep architecture, the resulting Motion and Object Continuity (MOC) scheme can be instantiated using any baseline object detection model. Our results show large improvements in the performances of a SOTA model in terms of object discovery, convergence speed and overall latent object representations, particularly for playing Atari games. Overall, we show clear benefits of integrating motion and object continuity for downstream tasks, moving beyond object representation learning based only on reconstruction.


Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity

Recent self-supervised video representation learning methods have found ...

CoDo: Contrastive Learning with Downstream Background Invariance for Detection

The prior self-supervised learning researches mainly select image-level ...

Recent Advances in Autoencoder-Based Representation Learning

Learning useful representations with little or no supervision is a key c...

Generalization Analysis for Contrastive Representation Learning

Recently, contrastive learning has found impressive success in advancing...

Improvements to Self-Supervised Representation Learning for Masked Image Modeling

This paper explores improvements to the masked image modeling (MIM) para...

DHOG: Deep Hierarchical Object Grouping

Recently, a number of competitive methods have tackled unsupervised repr...

Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots

We introduce a method to segment the visual field into independently mov...