Datasets > Modality > Images > ECSSD (Extended Complex Scene Saliency Dataset)

ECSSD (Extended Complex Scene Saliency Dataset)

Introduced by Yan et al. in Hierarchical Saliency Detection

The Extended Complex Scene Saliency Dataset (ECSSD) is comprised of complex scenes, presenting textures and structures common to real-world images. ECSSD contains 1,000 intricate images and respective ground-truth saliency maps, created as an average of the labeling of five human participants.

Source: SAD: Saliency-based Defenses Against Adversarial Examples

Samples

License

  • Unknown

Modalities

Languages

Tasks