Paper Info
Title
Where Should Saliency Models Look Next?
Abstract
Recently, large breakthroughs have been observed in saliency modeling. The top scores on saliency benchmarks have become dominated by neural network models of saliency, and some evaluation scores have begun to saturate. Large jumps in performance relative to previous models can be found across datasets, image types, and evaluation metrics. Have saliency models begun to converge on human performance? In this paper, we re-examine the current state-of-the-art using a fine-grained analysis on image types, individual images, and image regions. Using experiments to gather annotations for high-density regions of human eye fixations on images in two established saliency datasets, MIT300 and CAT2000, we quantify up to 60% of the remaining errors of saliency models. We argue that to continue to approach human-level performance, saliency models will need to discover higher-level concepts in images: text, objects of gaze and action, locations of motion, and expected locations of people in images. Moreover, they will need to reason about the relative importance of image regions, such as focusing on the most important person in the room or the most informative sign on the road. More accurately tracking performance will require finer-grained evaluations and metrics. Pushing performance further will require higher-level image understanding.
Year
DOI
Venue
2016
10.1007/978-3-319-46454-1_49
COMPUTER VISION - ECCV 2016, PT V
Keywords
Field
DocType
Saliency maps, Saliency estimation, Eye movements, Deep learning, Image understanding
Human eye,Computer vision,Fixation (psychology),Gaze,Computer science,Salience (neuroscience),Eye movement,Artificial intelligence,Deep learning,Artificial neural network
Conference
Volume
ISSN
Citations 
9909
0302-9743
34
PageRank 
References 
Authors
0.99
14
6
Name
Order
Citations
PageRank
Zoya Gavrilov128716.20
Adrià Recasens2746.55
Ali Borji3198578.50
Aude Oliva45121298.19
Antonio Torralba514607956.27
Frédo Durand68625414.94