Deeply supervised salient object detection with short connections
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based on Fully Convolutional Neural Networks (FCNs). There is still a large room for improvement over the generic FCN models that do not explicitly deal with the scale-space problem. Holistically-Nested Edge Detector (HED) provides a skip-layer structure with deep supervision for edge and boundary detection, but the performance gain of HED on salience detection is not obvious. In this paper, we propose a new method for saliency detection by introducing short connections to the skip-layer structures within the HED architecture. Our framework provides rich multi-scale feature maps at each layer, a property that is critically needed to perform segment detection. Our method produces state-of-the-art results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency (0.15 seconds per image), effectiveness, and simplicity over the existing algorithms.
Code (4)
Tasks
Boundary DetectionObjectobject-detectionObject DetectionRGB Salient Object DetectionSaliency DetectionSalient Object DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection
This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, t…
Saliency DetectionSaliency PredictionRicher and Deeper Supervision Network for Salient Object Detection
Recent Salient Object Detection (SOD) systems are mostly based on Convolutional Neural Networks (CNNs). Specifically, Deeply Supervised Saliency (DSS) system has shown it is very useful to add short connections to the ne…
Objectobject-detectionObject DetectionRGB Salient Object Detection+1DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision …
object-detectionObject DetectionRGB Salient Object DetectionSaliency Prediction+1Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learning global representations for image-leve…
Objectobject-detectionObject DetectionRepresentation Learning+1Weakly Supervised Learning for Salient Object Detection
Recent advances in supervised salient object detection has resulted in significant performance on benchmark datasets. Training such models, however, requires expensive pixel-wise annotations of salient objects. Moreover,…
Objectobject-detectionObject DetectionRGB Salient Object Detection+3