A set of patters used in psychophysical research to evaluate the ability of saliency algorithms to find targets distinct from distractors in orientation, color and size. Each image is a 7x7 grid and contains a single target. All images are 1024x1024px and have corresponding ground truth masks for the target and distractors. Patterns and annotations are generated with Psychophysical Image Generator (PIG).
P3 Dataset Statistics
- Image size: 1024x1024
- Target size: 18 to 140 px
- Distractor size: 75px
- Target/distractor shapes: circle, rectangle, ellipse, bar
- One unique target per image (color, orientation or size)
- 2589 images:
- 885 with color targets
- 864 with orientation targets
- 840 with size targets
Citation
- If you use this dataset please cite:
- I. Kotseruba, C. Wloka, A. Rasouli, J.K. Tsotsos, "Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations", BMVC, 2019.
-
@inproceedings{Kotseruba2019BMVC,
author = {Iuliia Kotseruba and Calden Wloka and Amir Rasouli and John K. Tsotsos},
title = {{Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations}},
booktitle = {British Machine Vision Conference (BMVC)},
year = {2019} }
©2019 Iuliia Kotseruba - Split Template by One Page Love
A set of realistic odd-one-out stimuli gathered "in the wild". Each image in the Odd-One-Out (O3) dataset depicts a scene with multiple objects similar to each other in appearance (distractors) and a singleton (target) distinct in one or more feature dimensions (e.g. color, shape, size). All images are resized so that the larger dimension is 1024px. Targets represent approx. 400 common object types such as flowers, sweets, chicken eggs, leaves, tiles and birds. Pixelwise masks are provided for targets and distractors. Annotations are generated using CVAT.
O3 Dataset Statistics
- Image size: 1024 in the largest dimension
- One unique target per image (color, orientation or size)
- 2001 images:
- 37% of targets differ by color
- 33% of the targets differ by texture
- 26% of the targets differ by shape
- 19% of the targets differ by size
- 8% of the targets differ by orientation
Citation
- If you use this dataset please cite:
- I. Kotseruba, C. Wloka, A. Rasouli, J.K. Tsotsos, "Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations", BMVC, 2019.
-
@inproceedings{Kotseruba2019BMVC,
author = {Iuliia Kotseruba and Calden Wloka and Amir Rasouli and John K. Tsotsos},
title = {{Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations}},
booktitle = {British Machine Vision Conference (BMVC)},
year = {2019} }