Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing

CVPR 2019 Kaihua Zhang Tengpeng Li Bo Liu Qingshan Liu

In image co-saliency detection problem, one critical issue is how to model the concurrent pattern of the co-salient parts, which appears both within each image and across all the relevant images. In this paper, we propose a hierarchical image co-saliency detection framework as a coarse to fine strategy to capture this pattern... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Co-Salient Object Detection CoCA CSMG S-Measure 0.627 # 2
max F-Measure 0.499 # 2
mean E-Measure 0.606 # 4
Mean F-measure 0.390 # 4
Co-Salient Object Detection CoSal2015 CSMG Average MAE 0.130 # 4
S-Measure 0.774 # 4
max F-Measure 0.784 # 4
max E-Measure 0.842 # 4
Co-Salient Object Detection CoSOD3k CSMG S-Measure 0.711 # 3
max E-Measure 0.804 # 2
max F-Measure 0.709 # 2
Average MAE 0.157 # 3

Methods used in the Paper