This repository contains a mapping between the classes of COCO, LVIS, and Open Images V4 datasets into a unique set of 1460 classes.

COCO [Lin et al 2014] contains 80 classes, LVIS [gupta2019lvis] contains 1460 classes, Open Images V4 [Kuznetsova et al. 2020] contains 601 classes.

We built a mapping of these classes using a semi-automatic procedure in order to have a unique final list of 1460 classes. We also generated a hierarchy for each class, using wordnet

This repository contains the following files:

coco_classes_map.txt, contains the mapping for the 80 coco classes

lvis_classes_map.txt, contains the mapping for the 1460 coco classes

openimages_classes_map.txt, contains the mapping for the 601 coco classes

classname_hyperset_definition.csv, contains the final set of 1460 classes, their definition and hierarchy

all-classnames.xlsx, contains a side-by-side view of all classes considered

This mapping was used in VISIONE [Amato et al. 2021, Amato et al. 2022] that is a content-based retrieval system that supports various search functionalities (text search, object/color-based search, semantic and visual similarity search, temporal search). For the object detection VISIONE uses three pre-trained models: VfNet Zhang et al. 2021, Mask R-CNN He et al. 2017, and a Faster R-CNN+Inception ResNet (trained on the Open Images V4).

This is repository is released under a Creative Commons Attribution license, please cite the following paper if you use it in your work in any form:

@inproceedings{amato2021visione, title={The visione video search system: exploiting off-the-shelf text search engines for large-scale video retrieval}, author={Amato, Giuseppe and Bolettieri, Paolo and Carrara, Fabio and Debole, Franca and Falchi, Fabrizio and Gennaro, Claudio and Vadicamo, Lucia and Vairo, Claudio}, journal={Journal of Imaging}, volume={7}, number={5}, pages={76}, year={2021}, publisher={Multidisciplinary Digital Publishing Institute} }

References:

[Amato et al. 2022] Amato, G. et al. (2022). VISIONE at Video Browser Showdown 2022. In: , et al. MultiMedia Modeling. MMM 2022. Lecture Notes in Computer Science, vol 13142. Springer, Cham. https://doi.org/10.1007/978-3-030-98355-0_52

[Amato et al. 2021] Amato, G., Bolettieri, P., Carrara, F., Debole, F., Falchi, F., Gennaro, C., Vadicamo, L. and Vairo, C., 2021. The visione video search system: exploiting off-the-shelf text search engines for large-scale video retrieval. Journal of Imaging, 7(5), p.76.

[Gupta et al.2019] Gupta, A., Dollar, P. and Girshick, R., 2019. Lvis: A dataset for large vocabulary instance segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 5356-5364).

[He et al. 2017] He, K., Gkioxari, G., Dollár, P. and Girshick, R., 2017. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969).

[Kuznetsova et al. 2020] Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A. and Duerig, T., 2020. The open images dataset v4. International Journal of Computer Vision, 128(7), pp.1956-1981.

[Lin et al. 2014] Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P. and Zitnick, C.L., 2014, September. Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740-755). Springer, Cham.

[Zhang et al. 2021] Zhang, H., Wang, Y., Dayoub, F. and Sunderhauf, N., 2021. Varifocalnet: An iou-aware dense object detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8514-8523).

Context

This dataset contains pickled Python objects with data from the annotations of the Microsoft (MS) COCO dataset. COCO is a large-scale object detection, segmentation, and captioning dataset.

Content

Except for the objs file, which is a plain text file continuing a list of objects, the data in this dataset is all in the pickle format, a way of storing Python objects at binary data files.

Important: These pickles were pickled using Python 2. Since Kernels use Python 3, you will need to specify the encoding when unpickling these files. The Python utility scripts here have been updated to correctly unpickle these files.

# the correct syntax to read these pickled files into Python 3
pickle.load(open('file_path, 'rb'), encoding = "latin1")

Acknowledgements

As a derivative of the original COCO dataset, this dataset is distributed under a CC-BY 4.0 license. These files were distributed as part of the supporting materials for Zhao et al 2017. If you use these files in your work, please cite the following paper:

Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K. W. (2017). Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (pp. 2979-2989).

Extract the file , go to data -> Data . You will find directories with names 'bear' , 'bicycle' , 'bus' , 'car' , 'cat', 'cow' , 'dog' , 'elephant' , 'fire_hydrant' , 'motorcycle' , 'person' ,'sheep' , 'stop_sign' , 'traffic_light' , 'train' ,'truck'. Each directory contains positive sample images for the said class (directory name) . The images have been extracted from COCO 2017 Validation images using the ground truth annotations . The datasets can be used for One-to-Rest Support Vector Machine classification after applying HOG feature extraction on each image . The data can also be used to train region suggestion algorithms for object detection . Each image is named in following format - (name of the image from COCO val2017 from where extracted)_(x)_(y)_(w)_(h).jpg , where x,y,w,h are annotations (Xmin, Ymin , width , height)