RECORD
Salient Object Detection for Images Taken by People With Vision Impairments
Computer Vision and Pattern Recognition · Submitted 12 Jan 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim 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.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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 .
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | 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. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | 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. | contribution 0.99 | 0.96 | 0.05 | asserted 1.00 |
| s2 | 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). | contribution 0.74 | 0.92 | 0.10 | asserted 1.00 |
| s3 | 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. | result 1.00 | 0.97 | 0.62 | asserted 1.00 |
| s4 | 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 . | future work 0.94 | 0.30 | 0.03 | unclear 0.72 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
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 .
Human review
How the literature uses it
2 arXiv papers cite this in 2 sentences
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.