PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos

Alex N Wang, Christopher Hoang, Yuwen Xiong, Yann LeCun, Mengye Ren

Keywords: computer vision, representation learning, self-supervised learning, egocentric video, visual representation

TL;DR: We uncover challenges of applying self-supervised learning to naturalistic, dense video data and propose a unified dense and pooled objective alongside architectural improvements to learn an effective visual representation.

Abstract:

Self-supervised learning has driven significant progress in learning from single-subject, _iconic_ images.
However, there are still unanswered questions about the use of minimally-curated, naturalistic video data, which contain _dense_ scenes with many independent objects, imbalanced class distributions, and varying object sizes.
In this paper, we propose PooDLe, a self-supervised learning method that combines an invariance-based objective on pooled representations with a dense SSL objective that enforces equivariance to optical flow warping.
Our results show that a unified objective applied at multiple feature scales is essential for learning effective image representations from naturalistic videos.
We validate our method with experiments on the BDD100K driving video dataset and the Walking Tours first-person video dataset, demonstrating its ability to capture spatial understanding from a dense objective and semantic understanding via a pooled representation objective.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7601