Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
This work addresses the need for more accurate saliency detection in computer vision, though it is incremental by building on existing multi-scale and message-passing approaches.
The paper tackled the problem of salient object detection by introducing a novel cascade CRFs architecture that jointly refines deep features and predictions through message-passing between features and predictions, achieving highly competitive performance on six datasets.
Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many approaches introduce message-passing to enhance CNN features or predictions. However, the messages are mainly transmitted in two ways, by feature-to-feature passing, and by prediction-to-prediction passing. In this paper, we add message-passing between features and predictions and propose a deep unified CRF saliency model . We design a novel cascade CRFs architecture with CNN to jointly refine deep features and predictions at each scale and progressively compute a final refined saliency map. We formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-prediction, from the coarse scale to the finer scale, to update the features and the corresponding predictions. Also, we formulate the mean-field updates for joint end-to-end model training with CNN through back propagation. The proposed deep unified CRF saliency model is evaluated over six datasets and shows highly competitive performance among the state of the arts.