PatternCom
- Citation Author(s):
-
Bill Psomas
(Czech Technical University in Prague)
- Submitted by:
- Vasileios Psomas
- Last updated:
- DOI:
- 10.21227/4xms-kh90
1 view
- Categories:
- Keywords:
Abstract
PatternCom is a composed image retrieval benchmark based on PatternNet. PatternNet is a large-scale high-resolution remote sensing image retrieval dataset. There are 38 classes and each class has 800 images of size 256×256 pixels. In PatternCom, we select some classes to be depicted in query images, and add a query text that defines an attribute relevant to that class. For instance, query images of “swimming pools” are combined with text queries defining “shape” as “rectangular”, “oval”, and “kidney-shaped”. In total, PatternCom includes six attributes consisted of up to four different classes each. Each attribute can be associated with two to five values per class. The number of positives ranges from 2 to 1345 and there are more than 21k queries in total.
Instructions:
Dataset
PatternCom is based on PatternNet, a large-scale, high-resolution remote sensing dataset that comprises 38 classes, with each class containing 800 images of 256×256 pixels.
Download PatternNet from this link and unzip it into a folder named PatternNet/. Then, download patternnet.csv from here and place it in the same folder. Finally, download the PatternCom attribute queries from this link and place them into the same PatternNet/ folder.
The final PatternNet/ folder structure should look like this:
PatternNet/
├── images/
├── PatternCom/
│ ├── color.csv
│ ├── context.csv
│ ├── density.csv
│ ├── existence.csv
│ ├── quantity.csv
│ └── shape.csv
├── patternnet.csv
└── patternnet_description.pdf
