paper-with-me

Papers

Deeply supervised salient object detection with short connections

2016-11-15 · CVPR 2017 7 · Qibin Hou, Ming-Ming Cheng, Xiao-Wei Hu, Ali Borji, Zhuowen Tu, Philip Torr

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.

📄 PDF Abstract BibTeX arXiv:1611.04849

Code (4)

AceCoooool/DSS-pytorch pytorch
Andrew-Qibin/DSS caffe2
houqb/DSS caffe2
moothes/salod pytorch

Tasks

Boundary DetectionObjectobject-detectionObject DetectionRGB Salient Object DetectionSaliency DetectionSalient Object DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
FCN Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as…

Similar Papers 제목 키워드 기반

Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection

2016-08-18 · Youbao Tang, Xiangqian Wu, Wei Bu

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 Prediction

Richer and Deeper Supervision Network for Salient Object Detection

2019-01-08 · Sen Jia, Neil D. B. Bruce

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+1

DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

2019-03-28 · Yun Liu, Ming-Ming Cheng, Xin-Yu Zhang, Guang-Yu Nie 외

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+1

Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors

2021-03-08 · Jian Ding, Enze Xie, Hang Xu, Chenhan Jiang 외

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+1

Weakly Supervised Learning for Salient Object Detection

2015-01-29 · Huaizu Jiang

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