# Salient Region Segmentation

## TL;DR

This paper redefines saliency prediction as a segmentation task, enabling faster training and comparable accuracy to regression-based models, while aligning with psychophysical insights.

## Contribution

It introduces a segmentation-based approach to saliency prediction, offering faster convergence and interpretability over traditional regression models.

## Key findings

- Faster convergence compared to regression models
- Performance comparable to state-of-the-art
- Features align with psychophysical insights

## Abstract

Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough, a new cohort of models were proposed based on neural network architectures, allowing significantly higher gaze prediction than previous shallow models, on all metrics. However, most models treat the saliency prediction as a \textit{regression} problem, and accurate regression of high-dimensional data is known to be a hard problem. Furthermore, it is unclear that intermediate levels of saliency (ie, neither very high, nor very low) are meaningful: Something is either salient, or it is not. Drawing from those two observations, we reformulate the saliency prediction problem as a salient region \textit{segmentation} problem. We demonstrate that the reformulation allows for faster convergence than the classical regression problem, while performance is comparable to state-of-the-art. We also visualise the general features learned by the model, which are showed to be consistent with insights from psychophysics.