What is a salient object? A dataset and a baseline model for salient object detection
Ali Borji

TL;DR
This paper introduces new datasets with multiple objects for salient object detection, analyzes the relationship between fixations and saliency, and proposes a simple baseline model that outperforms existing models on challenging data.
Contribution
It provides less biased datasets, a detailed analysis of fixation and saliency agreement, and a simple baseline model for evaluating salient object detection methods.
Findings
Existing models perform poorly on new datasets with multiple objects.
Most salient object correlates with the highest fixation fraction.
Baseline superpixel-based model is competitive and highlights segmentation issues.
Abstract
Salient object detection or salient region detection models, diverging from fixation prediction models, have traditionally been dealing with locating and segmenting the most salient object or region in a scene. While the notion of most salient object is sensible when multiple objects exist in a scene, current datasets for evaluation of saliency detection approaches often have scenes with only one single object. We introduce three main contributions in this paper: First, we take an indepth look at the problem of salient object detection by studying the relationship between where people look in scenes and what they choose as the most salient object when they are explicitly asked. Based on the agreement between fixations and saliency judgments, we then suggest that the most salient object is the one that attracts the highest fraction of fixations. Second, we provide two new less biased…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
