Salient Object Detection for Images Taken by People With Vision Impairments
This work addresses the problem of improving salient object detection for visually impaired users by providing a large, domain-specific dataset with unique characteristics.
The authors introduced VizWiz-SalientObject, a new dataset of 32,000 human-annotated images for salient object detection, collected from visually impaired individuals, and found that existing methods struggle with large objects, less complex boundaries, lack of text, and lower image quality.
Salient object detection is the task of producing a binary mask for an image that deciphers which pixels belong to the foreground object versus background. We introduce a new salient object detection dataset using images taken by people who are visually impaired who were seeking to better understand their surroundings, which we call VizWiz-SalientObject. Compared to seven existing datasets, VizWiz-SalientObject is the largest (i.e., 32,000 human-annotated images) and contains unique characteristics including a higher prevalence of text in the salient objects (i.e., in 68\% of images) and salient objects that occupy a larger ratio of the images (i.e., on average, $\sim$50\% coverage). We benchmarked seven modern salient object detection methods on our dataset and found they struggle most with images featuring salient objects that are large, have less complex boundaries, and lack text as well as for lower quality images. We invite the broader community to work on our new dataset challenge by publicly sharing the dataset at https://vizwiz.org/tasks-and-datasets/salient-object .