Future Slot Prediction for Unsupervised Object Discovery in Surgical Video

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Guiqiu, Jogan, Matjaz, Hussing, Marcel, Zhang, Edward, Eaton, Eric, Hashimoto, Daniel A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908439749328896
author Liao, Guiqiu
Jogan, Matjaz
Hussing, Marcel
Zhang, Edward
Eaton, Eric
Hashimoto, Daniel A.
author_facet Liao, Guiqiu
Jogan, Matjaz
Hussing, Marcel
Zhang, Edward
Eaton, Eric
Hashimoto, Daniel A.
contents Object-centric slot attention is an emerging paradigm for unsupervised learning of structured, interpretable object-centric representations (slots). This enables effective reasoning about objects and events at a low computational cost and is thus applicable to critical healthcare applications, such as real-time interpretation of surgical video. The heterogeneous scenes in real-world applications like surgery are, however, difficult to parse into a meaningful set of slots. Current approaches with an adaptive slot count perform well on images, but their performance on surgical videos is low. To address this challenge, we propose a dynamic temporal slot transformer (DTST) module that is trained both for temporal reasoning and for predicting the optimal future slot initialization. The model achieves state-of-the-art performance on multiple surgical databases, demonstrating that unsupervised object-centric methods can be applied to real-world data and become part of the common arsenal in healthcare applications.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01882
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Future Slot Prediction for Unsupervised Object Discovery in Surgical Video
Liao, Guiqiu
Jogan, Matjaz
Hussing, Marcel
Zhang, Edward
Eaton, Eric
Hashimoto, Daniel A.
Computer Vision and Pattern Recognition
Object-centric slot attention is an emerging paradigm for unsupervised learning of structured, interpretable object-centric representations (slots). This enables effective reasoning about objects and events at a low computational cost and is thus applicable to critical healthcare applications, such as real-time interpretation of surgical video. The heterogeneous scenes in real-world applications like surgery are, however, difficult to parse into a meaningful set of slots. Current approaches with an adaptive slot count perform well on images, but their performance on surgical videos is low. To address this challenge, we propose a dynamic temporal slot transformer (DTST) module that is trained both for temporal reasoning and for predicting the optimal future slot initialization. The model achieves state-of-the-art performance on multiple surgical databases, demonstrating that unsupervised object-centric methods can be applied to real-world data and become part of the common arsenal in healthcare applications.
title Future Slot Prediction for Unsupervised Object Discovery in Surgical Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.01882