OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction

TL;DR

This paper introduces OAT, a transformer-based model that predicts human gaze scanpaths during visual search by focusing on objects rather than pixels, improving alignment with human attention patterns.

Contribution

The paper presents a novel object-level attention transformer architecture with a new positional encoding for predicting human scanpaths in cluttered scenes.

Findings

OAT outperforms pixel-based models on established metrics.

OAT generalizes well to unseen layouts and objects.

OAT's predictions closely match human gaze behavior.

Abstract

Visual search is important in our daily life. The efficient allocation of visual attention is critical to effectively complete visual search tasks. Prior research has predominantly modelled the spatial allocation of visual attention in images at the pixel level, e.g. using a saliency map. However, emerging evidence shows that visual attention is guided by objects rather than pixel intensities. This paper introduces the Object-level Attention Transformer (OAT), which predicts human scanpaths as they search for a target object within a cluttered scene of distractors. OAT uses an encoder-decoder architecture. The encoder captures information about the position and appearance of the objects within an image and about the target. The decoder predicts the gaze scanpath as a sequence of object fixations, by integrating output features from both the encoder and decoder. We also propose a new positional encoding that better reflects spatial relationships between objects. We evaluated OAT on the Amazon book cover dataset and a new dataset for visual search that we collected. OAT's predicted gaze scanpaths align more closely with human gaze patterns, compared to predictions by algorithms based on spatial attention on both established metrics and a novel behavioural-based metric. Our results demonstrate the generalization ability of OAT, as it accurately predicts human scanpaths for unseen layouts and target objects.