The Role of Recurrency in Image Segmentation for Noisy and Limited Sample Settings

TL;DR

This paper investigates whether adding recurrent mechanisms to image segmentation models improves performance in noisy and limited data scenarios, finding that recurrence alone does not outperform feed-forward architectures.

Contribution

The study systematically explores different types of recurrence in segmentation models and evaluates their effectiveness in challenging data conditions.

Findings

Recurrent models did not outperform feed-forward models in noisy settings.

Recurrency alone is insufficient to surpass state-of-the-art segmentation performance.

Additional techniques are needed to leverage recurrence effectively.

Abstract

The biological brain has inspired multiple advances in machine learning. However, most state-of-the-art models in computer vision do not operate like the human brain, simply because they are not capable of changing or improving their decisions/outputs based on a deeper analysis. The brain is recurrent, while these models are not. It is therefore relevant to explore what would be the impact of adding recurrent mechanisms to existing state-of-the-art architectures and to answer the question of whether recurrency can improve existing architectures. To this end, we build on a feed-forward segmentation model and explore multiple types of recurrency for image segmentation. We explore self-organizing, relational, and memory retrieval types of recurrency that minimize a specific energy function. In our experiments, we tested these models on artificial and medical imaging data, while analyzing the impact of high levels of noise and few-shot learning settings. Our results do not validate our initial hypothesis that recurrent models should perform better in these settings, suggesting that these recurrent architectures, by themselves, are not sufficient to surpass state-of-the-art feed-forward versions and that additional work needs to be done on the topic.