SALICON (Salicency in Context)

Introduced by Jiang et al. in SALICON: Saliency in Context

The SALIency in CONtext (SALICON) dataset contains 10,000 training images, 5,000 validation images and 5,000 test images for saliency prediction. This dataset has been created by annotating saliency in images from MS COCO. The ground-truth saliency annotations include fixations generated from mouse trajectories. To improve the data quality, isolated fixations with low local density have been excluded. The training and validation sets, provided with ground truth, contain the following data fields: image, resolution and gaze. The testing data contains only the image and resolution fields.

Source: DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Few-Shot Transfer Learning for Saliency Prediction	SALICON->WebpageSaliency - 1-shot	DINet+FT\|Ref
Few-Shot Transfer Learning for Saliency Prediction	SALICON->WebpageSaliency - 5-shot	DINet+FT\|Ref
Few-Shot Transfer Learning for Saliency Prediction	SALICON->WebpageSaliency - 10-shot	DINet+FT\|Ref
Few-Shot Transfer Learning for Saliency Prediction	SALICON->WebpageSaliency - EUB	DINet+FT\|Ref
Saliency Prediction	SALICON	TranSalNet