Spurious Equilibrium in Segmentation Models and Recurrent Processing in Human Vision
Track: regular paper (up to 6 pages)
Keywords: Spurious Correlation, Segmentation Model, Cognitive Science
TL;DR: Instance segmentation models when trained can cause errors in models that rely solely on models that rely on single stage decision making using feed-forward networks.
Abstract: Iterative decision-making has been widely studied in human cognition and is recognized for its energy efficiency and suitability for biological computations. In contrast, instance segmentation models adopt strategies that diverge from human vision, each presenting unique strengths and limitations. In this paper, we examine the grouping problem in segmentation models and demonstrate that iterative recurrent processing facilitates the identification of diverse solutions and can enhance grouping capabilities. Our experiments further reveal that recurrent processing accelerates convergence and can generate diverse solutions that can help mitigate suboptimal spurious minima. Our work focuses on confounding cases, which have become increasingly relevant as systems are increasingly deployed in safety-critical environments.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Presenter: ~Kailas_D1
Format: Yes, the presenting author will attend in person if this work is accepted to the workshop.
Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.
Submission Number: 36
Loading