CSSD Dataset

Estimated reading: 3 minutes

Visualization of the CSSD dataset in the Deep Lake UI

CSSD dataset

What is CSSD Dataset?

The CSSD (Complex Scene Saliency) Dataset is created to enhance research in the segmentation of complex scene saliency images. It was generated to substitute the MSRA-1000 dataset which normally has images having smooth and simple background structures. The dataset brings natural images which are diverse in nature. All the images were acquired from the internet and with help of five helpers in producing ground truth masks. This dataset contains 200 natural images with well-annotated masks.

Download CSSD Dataset in Python

Instead of downloading the CSSD dataset in Python, you can effortlessly load it in Python via our Deep Lake open-source with just one line of code.

Load CSSD Dataset in Python

				
					import deeplake
ds = deeplake.load("hub://activeloop/cssd")

CSSD Dataset Structure

CSSD Data Fields

images: tensor containing images
masks: tensor containing masks of respective images

How to use CSSD Dataset with PyTorch and TensorFlow in Python

Train a model on CSSD dataset with PyTorch in Python

Let’s use Deep Lake built-in PyTorch one-line dataloader to connect the data to the compute:

				
					dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)

Train a model on CSSD dataset with TensorFlow in Python

				
					dataloader = ds.tensorflow()

Additional Information about CSSD Dataset

CSSD Dataset Description

Homepage: https://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/dataset.html
Paper: Yan, Q., Xu, L., Shi, J., & Jia, J. (2013). Hierarchical saliency detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1155-1162).

CSSD Dataset Curators

Yan, Q., Xu, L., Shi, J., & Jia, J.

CSSD Dataset Licensing Information

Deep Lake users may have access to a variety of publicly available datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have a license to use the datasets. It is your responsibility to determine whether you have permission to use the datasets under their license.

If you’re a dataset owner and do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thank you for your contribution to the ML community!

CSSD Dataset Citation Information

				
					@inproceedings{yan2013hierarchical,
  title={Hierarchical saliency detection},
  author={Yan, Qiong and Xu, Li and Shi, Jianping and Jia, Jiaya},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1155--1162},
  year={2013}
}

CSSD Dataset FAQs

What is the CSSD dataset for Python?

CSSD dataset was produced to substitute the MSRA-1000 dataset which typically has pictures having smooth and straightforward foundation structures. The dataset brings normal pictures which are assorted in nature. Every one of the pictures was procured from the web and with the assistance of five assistants in creating ground truth covers. This dataset contains 200 normal pictures with very much clarified veils.

How to download the CSSD dataset in Python?

You can load the CSSD dataset fast with one line of code using the open-source package Activeloop Deep Lake in Python. See detailed instructions on how to load the CSSD dataset training subset in Python.

How can I use the CSSD dataset in PyTorch or TensorFlow?

You can stream the CSSD dataset while training a model in PyTorch or TensorFlow with one line of code using the open-source package Activeloop Deep Lake in Python. See detailed instructions on how to train a model on the CSSD dataset with PyTorch in Python or train a model on the CSSD dataset with TensorFlow in Python.