# Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations

arXiv: https://arxiv.org/abs/2005.06583 · HTML: https://mlsanity.com/paper/2005.06583/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2020.

## Built on by (most cited first, 10 of 10)

- [Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention](https://mlsanity.com/paper/2303.01542/) (2023)
- [Vision-Language Models Can't See the Obvious](https://mlsanity.com/paper/2507.04741/) (2025)
- [Dissecting Query-Key Interaction in Vision Transformers](https://mlsanity.com/paper/2405.14880/) (2024)
- [Measuring Human Perception to Improve Open Set Recognition](https://mlsanity.com/paper/2209.03519/) (2022)
- [What Do Deep Saliency Models Learn about Visual Attention?](https://mlsanity.com/paper/2310.09679/) (2023)
- [See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection](https://mlsanity.com/paper/2604.24339/) (2026)
- [Learning Saliency From Fixations](https://mlsanity.com/paper/2311.14073/) (2023)
- [Vision Transformer attention alignment with human visual perception in aesthetic object evaluation](https://mlsanity.com/paper/2507.17616/) (2025)
- [DeepRare: Generic Unsupervised Visual Attention Models](https://mlsanity.com/paper/2109.11439/) (2021)
- [Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task](https://mlsanity.com/paper/2607.01503/) (2026)

## Abstract (arXiv)

Recent advances in the field of saliency have concentrated on fixation prediction, with benchmarks reaching saturation. However, there is an extensive body of works in psychology and neuroscience that describe aspects of human visual attention that might not be adequately captured by current approaches. Here, we investigate singleton detection, which can be thought of as a canonical example of salience. We introduce two novel datasets, one with psychophysical patterns and one with natural odd-one-out stimuli. Using these datasets we demonstrate through extensive experimentation that nearly all saliency algorithms do not adequately respond to singleton targets in synthetic and natural images. Furthermore, we investigate the effect of training state-of-the-art CNN-based saliency models on these types of stimuli and conclude that the additional training data does not lead to a significant improvement of their ability to find odd-one-out targets. Datasets are available at http://data.nvision2.eecs.yorku.ca/P3O3/.