Saliency Detection with Recurrent Fully Convolutional Networks
نویسندگان
چکیده
• Employs three kind of low-level contrast features, including color, intensity and orientation, and the center prior knowledge to introduce saliency prior maps. • Train the RFCN with two stage training strategy, pre-training on the segmentation data set and fine-tuning on the saliency data set. The recurrent structure can incorporate the saliency prior maps into the CNNs with an end-to-end training method. • Refine the saliency maps with a postprocessing method which can improve the performance of RFCN. Edge-preserving maps are produced with the computation of color confidence and spatial confidence. 3. Algorithm 4. Results
منابع مشابه
Weakly Supervised Salient Object Detection Using Image Labels
Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps fro...
متن کاملContrast-Oriented Deep Neural Networks for Salient Object Detection
Deep convolutional neural networks have become a key element in the recent breakthrough of salient object detection. However, existing CNN-based methods are based on either patchwise (region-wise) training and inference or fully convolutional networks. Methods in the former category are generally timeconsuming due to severe storage and computational redundancies among overlapping patches. To ov...
متن کاملAgile Amulet: Real-Time Salient Object Detection with Contextual Attention
This paper proposes an Agile Aggregating Multi-Level feaTure framework (Agile Amulet) for salient object detection. The Agile Amulet builds on previous works to predict saliency maps using multi-level convolutional features. Compared to previous works, Agile Amulet employs some key innovations to improve training and testing speed while also increase prediction accuracy. More specifically, we f...
متن کاملPaying More Attention to Saliency: Image Captioning with Saliency and Context Attention
Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction ...
متن کاملA Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection
—Traditional saliency models usually adopt hand-crafted image features and human-designed mechanisms to calculate local or global contrast. In this paper, we propose a novel computational saliency model, i.e., deep spatial contextual long-term recurrent convolutional network (DSCLRCN) to predict where people looks in natural scenes. DSCLRCN first automatically learns saliency related local feat...
متن کامل