Saliency Optimization from Robust Background Detection

CVPR 2014 Wangjiang ZhuShuang LiangYichen WeiJian Sun

Recent progresses in salient object detection have exploited the boundary prior, or background information, to assist other saliency cues such as contrast, achieving state-of-the-art results. However, their usage of boundary prior is very simple, fragile, and the integration with other cues is mostly heuristic... (read more)

PDF Abstract

Evaluation results from the paper

 SOTA for Object Detection on Caltech Lanes Cordova (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Object Detection Caltech Lanes Cordova ca Accuracy 92 # 1