scispace - formally typeset
Open AccessProceedings ArticleDOI

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

TLDR
Amulet is presented, a generic aggregating multi-level convolutional feature framework for salient object detection that provides accurate salient object labeling and performs favorably against state-of-the-art approaches in terms of near all compared evaluation metrics.
Abstract
Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. However, how to better aggregate multi-level convolutional feature maps for salient object detection is underexplored. In this work, we present Amulet, a generic aggregating multi-level convolutional feature framework for salient object detection. Our framework first integrates multi-level feature maps into multiple resolutions, which simultaneously incorporate coarse semantics and fine details. Then it adaptively learns to combine these feature maps at each resolution and predict saliency maps with the combined features. Finally, the predicted results are efficiently fused to generate the final saliency map. In addition, to achieve accurate boundary inference and semantic enhancement, edge-aware feature maps in low-level layers and the predicted results of low resolution features are recursively embedded into the learning framework. By aggregating multi-level convolutional features in this efficient and flexible manner, the proposed saliency model provides accurate salient object labeling. Comprehensive experiments demonstrate that our method performs favorably against state-of-the-art approaches in terms of near all compared evaluation metrics.

read more

Citations
More filters
Proceedings ArticleDOI

Depth-Aware Mirror Segmentation

TL;DR: Zhang et al. as discussed by the authors proposed a depth-aware mirror segmentation method that leverages depth estimates from ToF-based cameras as an additional cue to disambiguate challenging cases where the contrast or relation in RGB colors between the mirror reflection and the surrounding scene is subtle.
Journal ArticleDOI

Learning Deep Relations to Promote Saliency Detection

TL;DR: This paper explores the ubiquitous relations on the deep features to promote the existing saliency detectors efficiently and introduces a threshold-constrained training pair construction strategy to ensure that it can accurately estimate the relations between different image parts in a self-supervised way.
Book ChapterDOI

A Segmentation-Aware Deep Fusion Network for Compressed Sensing MRI

TL;DR: Wang et al. as discussed by the authors proposed a segmentation-aware deep fusion network called SADFN for compressed sensing MRI, which fused all the features from different layers in the segmentation network and provided aggregated feature maps containing semantic information to each layer in the reconstruction network with a feature fusion strategy.
Proceedings ArticleDOI

Boundary-Guided Camouflaged Object Detection

TL;DR: This paper proposes a novel boundary-guided network (BGNet) for camouflaged object detection, which significantly outperforms the existing 18 state-of-the-art methods under four widely-used evaluation metrics.
Posted Content

MobileSal: Extremely Efficient RGB-D Salient Object Detection.

TL;DR: Zhang et al. as discussed by the authors proposed an implicit depth restoration (IDR) technique to strengthen the feature representation capability of mobile networks for RGB-D salient object detection, which is only adopted in the training phase and is omitted during testing, so it is computationally free.
References
More filters
Proceedings ArticleDOI

Deep Residual Learning for Image Recognition

TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article

Very Deep Convolutional Networks for Large-Scale Image Recognition

TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article

Very Deep Convolutional Networks for Large-Scale Image Recognition

TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI

U-Net: Convolutional Networks for Biomedical Image Segmentation

TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Proceedings ArticleDOI

Fully convolutional networks for semantic segmentation

TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Related Papers (5)