This post summarized the most used benchmark datasets for the Image Matching Task.
| Dataset name | Size (pairs) | Class | Source datasets | Annotations | Characteristics |
|---|---|---|---|---|---|
| Caltech-101 | 1,515 | 101 | Caltech-101 | object segmentation | tightly cropped images of objects, little background |
| PASCAL-PARTS | 3,884 | 20 | PASCAL-PARTS PASCAL3D+ | keypoints (0~12), azimuth, elevation, cyclo-rotation, body part segmentation | tightly cropped images of objects, little background, part and 3D information |
| Animal-parts | ≈7,000 | 100 | ILSVRC 2012 | keypoints (1~6) | keypoints limited to eyes and feet of animals |
| CUB-200-2011 | 120k | 200 | CUB-200-2011 | 15 part locations, 312 binary attributes, bbox | tightly cropped images of object, only bird images |
| TSS | 400 | 9 | FG3DCar, JODS, PASCAL | object segmentation, flow, vectors | cropped images of objects, moderate background |
| PF-WILLOW | 900 | 5 | PASCAL VOC 2007, Caltech-256 | keypoints (10) | center-aligned images, pairs with the same viewpoint |
| PF-PASCAL | 1,300 | 20 | PASCAL VOC 2007 | keypoints (4~17), bbox | pairs with the same viewpoint |
| SPair-71k | 70,958 | 18 | PASCAL3D+, PASCAL VOC 2012 | keypoints (3~30), azimuth, viewpoint diff., scale diff., trunc. diff., occl. diff., object seg., bbox | large-scale data with diverse variations, rich annotations, clear dataset splits |
CUB-200-2011
- Paper: C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, “The Caltech-UCSD birds-200–2011 dataset,” Tech. Rep., 2011.
- Contains 11,788 images of 200 bird categories, with 15 parts annotated
TSS dataset
- Paper: T. Taniai, S. N. Sinha, and Y. Sato, “Joint recovery of dense correspondence and cosegmentation in two images,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 4246–4255.
- Consists of 400 image pairs divided into three groups: FG3DCar, JODS, and PASCAL
PF-WILLOW dataset
- Paper: B. Ham, M. Cho, C. Schmid, and J. Ponce, “Proposal flow,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 3475–3484.
- Includes 10 object sub-classes with 10 keypoint annotations for each image.
- Download: https://www.di.ens.fr/willow/research/proposalflow/
PF-PASCAL
- Paper: B. Ham, M. Cho, C. Schmid, and J. Ponce, “Proposal flow,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 3475–3484.
- Contains 1,351 image pairs for 20 object categories with PASCAL keypoint annotations
- Download: https://www.di.ens.fr/willow/research/proposalflow/
SPair-71k
- Paper: J. Min, J. Lee, J. Ponce, and M. Cho, “Hyperpixel flow: Semantic correspondence with multi-layer neural features,” in Proc. IEEE Int. Conf. Comput. Vis., 2019, pp. 3395–3404.
- Provides 70,958 image pairs of 18 object categories with ground-truth annotations for object bounding boxes, segmentation masks, and keypoints. The image pairs feature various changes in viewpoint, scale, truncation, and occlusion.