Top down saliency estimation via superpixel-based discriminative dictionaries
نویسندگان
چکیده
Predicting where humans look in images has gained significant popularity in recent years. In this work, we present a novel method for learning top-down visual saliency, which is well-suited to locate objects of interest in complex scenes. During training, we jointly learn a superpixel based class-specific dictionary and a Conditional Random Field (CRF). While using such a discriminative dictionary helps to distinguish target objects from the background, performing the computations at the superpixel level allows us to improve accuracy of object localizations. Experimental results on the Graz-02 and PASCAL VOC 2007 datasets show that the proposed approach is able to achieve stateof-the-art results and provides much better saliency maps.
منابع مشابه
Top down saliency estimation via superpixel-based discriminative dictionaries: Supplementary material
More salient object detection results can be seen in Figure 1, Figure 2 and Figure 3 for the bike, car and people classes in the Graz-02 dataset, respectively. For each class, we both present the results of Alexe et al.’s generic objectness map [1] (on superpixel-level), Yang and Yang’s top-down salient object detection method [2] and the proposed method (setting 3). To distinguish between task...
متن کاملWeakly Supervised Top-down Salient Object Detection
Top-down saliency models produce a probability map that peaks at target locations specified by a task/goal such as object detection. They are usually trained in a fully supervised setting involving pixel-level annotations of objects. We propose a weakly supervised top-down saliency framework using only binary labels that indicate the presence/absence of an object in an image. First, the probabi...
متن کاملIntegrating Object Affordances with Artificial Visual Attention
Affordances, as for example grasping possibilities, are known to play a role in the guidance of human attention but have not been considered in artificial attention systems so far. Extending our earlier work, we investigate the combination of affordance estimation and visual saliency in an artificial visual attention model. Different models based on saliency, affordance estimation, or their com...
متن کاملSaliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs
This paper proposes a novel saliency detection method by combining region-level saliency estimation and pixel-level saliency prediction with CNNs (denoted as CRPSD). For pixel-level saliency prediction, a fully convolutional neural network (called pixel-level CNN) is constructed by modifying the VGGNet architecture to perform multiscale feature learning, based on which an image-to-image predict...
متن کاملA parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos
Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these m...
متن کامل