Graph Matching

The Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset is the most widely-used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds, 5,994 for training and 5,794 for testing. Each image has detailed annotations: 1 subcategory label, 15 part locations, 312 binary attributes and 1 bounding box. The textual information comes from Reed et al.. They expand the CUB-200-2011 dataset by collecting fine-grained natural language descriptions. Ten single-sentence descriptions are collected for each image. The natural language descriptions are collected through the Amazon Mechanical Turk (AMT) platform, and are required at least 10 words, without any information of subcategories and actions. Source: Fine-grained Visual-textual Representation Learning Image Source: http://www.vision.caltech.edu/visipedia/CUB-200-2011.html

The PASCAL Visual Object Classes (VOC) 2012 dataset contains 20 object categories including vehicles, household, animals, and other: aeroplane, bicycle, boat, bus, car, motorbike, train, bottle, chair, dining table, potted plant, sofa, TV/monitor, bird, cat, cow, dog, horse, sheep, and person. Each image in this dataset has pixel-level segmentation annotations, bounding box annotations, and object class annotations. This dataset has been widely used as a benchmark for object detection, semantic segmentation, and classification tasks. The PASCAL VOC dataset is split into three subsets: 1,464 images for training, 1,449 images for validation and a private testing set. Source: Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey Image Source: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/examples/images/sheep_06.jpg

SPair-71k contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations. Source: SPair-71k: A Large-scale Benchmark for Semantic Correspondence Image Source: http://cvlab.postech.ac.kr/research/SPair-71k/

Occluded REID is an occluded person dataset captured by mobile cameras, consisting of 2,000 images of 200 occluded persons (see Fig. (c)). Each identity has 5 full-body person images and 5 occluded person images with different types of occlusion. Source: Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification Image Source: https://github.com/tinajia2012/ICME2018_Occluded-Person-Reidentification_datasets

The BirdSong dataset consists of audio recordings of bird songs at the H. J. Andrews (HJA) Experimental Forest, using unattended microphones. The goal of the dataset is to provide data to automatically identify the species of bird responsible for each utterance in these recordings. The dataset contains 548 10-seconds audio recordings.

The LINUX dataset consists of 48,747 Program Dependence Graphs (PDG) generated from the Linux kernel. Each graph represents a function, where a node represents one statement and an edge represents the dependency between the two statements Source: Convolutional Set Matching for Graph Similarity

Mindboggle is a large publicly available dataset of manually labeled brain MRI. It consists of 101 subjects collected from different sites, with cortical meshes varying from 102K to 185K vertices. Each brain surface contains 25 or 31 manually labeled parcels. Source: Graph Convolutions on Spectral Embeddings: Learning of Cortical Surface Data Image Source: https://mindboggle.info/data.html

RARE consists of English AMR pairs with similarity scores that reflect the structural differences between them. Given that AMRs are graphical representations of text, an AMR similarity metric should be sensitive to structural variations between AMRs, even if its labels remain unchanged. Since there is no established evaluation of AMR metrics on structural similarity, we have developed a new benchmark dataset called Randomized AMRs with Rewired Edges (RARE). RARE consists of English AMR pairs with similarity scores that reflect the structural differences between them. It can be used to evaluate AMR metrics on their sensitivity at detecting structural changes between pairs of AMRs.

The DispScenes dataset was created to address the specific problem of disparate image matching. The image pairs in all the datasets exhibit high levels of variation in illumination and viewpoint and also contain instances of occlusion. The DispScenes dataset provides manual ground truth keypoint correspondences for all images. Source: Matching Disparate Image Pairs Using Shape-Aware ConvNets

IMCPT-SparseGM dataset is a new visual graph matching benchmark addressing partial matching and graphs with larger sizes, based on the novel stereo benchmark Image Matching Challenge PhotoTourism (IMC-PT) 2020. This dataset is released in CVPR 2023 paper Deep Learning of Partial Graph Matching via Differentiable Top-K. | # images | # classes | avg # nodes | avg # edges | # universe | partial rate | | ------------ | ------------- | --------------- | ----------- | -------------- | ---------------- | | 25765 | 16 | 44.48 | 123.99 | 100 | 55.5% |

IMCPT-SparseGM dataset is a new visual graph matching benchmark addressing partial matching and graphs with larger sizes, based on the novel stereo benchmark Image Matching Challenge PhotoTourism (IMC-PT) 2020. This dataset is released in CVPR 2023 paper Deep Learning of Partial Graph Matching via Differentiable Top-K. | # images | # classes | avg # nodes | avg # edges | # universe | partial rate | | ------------ | ------------- | --------------- | ----------- | -------------- | ---------------- | | 25765 | 16 | 21.36 | 54.71 | 50 | 57.3% |