paper-with-me

홈 › Papers

Attentive Feedback Network for Boundary-Aware Salient Object Detection

2019-06-01 · CVPR 2019 6 · Mengyang Feng, Huchuan Lu, Errui Ding

Recent deep learning based salient object detection methods achieve gratifying performance built upon Fully Convolutional Neural Networks (FCNs). However, most of them have suffered from the boundary challenge. The state-of-the-art methods employ feature aggregation tech- nique and can precisely find out wherein the salient object, but they often fail to segment out the entire object with fine boundaries, especially those raised narrow stripes. So there is still a large room for improvement over the FCN based models. In this paper, we design the Attentive Feedback Modules (AFMs) to better explore the structure of objects. A Boundary-Enhanced Loss (BEL) is further employed for learning exquisite boundaries. Our proposed deep model produces satisfying results on the object boundaries and achieves state-of-the-art performance on five widely tested salient object detection benchmarks. The network is in a fully convolutional fashion running at a speed of 26 FPS and does not need any post-processing.

📄 PDF Abstract BibTeX

Code (1)

ArcherFMY/AFNet

Tasks

Objectobject-detectionObject DetectionRGB Salient Object DetectionSalient Object Detection

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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

Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images

2022-02-07 · Zhou Huang, Tian-Zhu Xiang, Huai-Xin Chen, Hang Dai

Existing CNNs-based salient object detection (SOD) heavily depends on the large-scale pixel-level annotations, which is labor-intensive, time-consuming, and expensive. By contrast, the sparse annotations become appealing…

Objectobject-detectionObject DetectionSalient Object Detection

Contour Loss: Boundary-Aware Learning for Salient Object Segmentation

2019-08-06 · Zixuan Chen, Huajun Zhou, Xiaohua Xie, Jian-Huang Lai

We present a learning model that makes full use of boundary information for salient object segmentation. Specifically, we come up with a novel loss function, i.e., Contour Loss, which leverages object contours to guide m…

GPUObjectSaliency DetectionSemantic Segmentation

Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery

2023-03-06 · Dejun Feng, Hongyu Chen, Suning Liu, Ziyang Liao 외

With the increasing application of deep learning in various domains, salient object detection in optical remote sensing images (ORSI-SOD) has attracted significant attention. However, most existing ORSI-SOD methods predo…

Decoderobject-detectionObject DetectionSalient Object Detection

Position-Aware Relation Learning for RGB-Thermal Salient Object Detection

2022-09-21 · Heng Zhou, Chunna Tian, Zhenxi Zhang, Chengyang Li 외

RGB-Thermal salient object detection (SOD) combines two spectra to segment visually conspicuous regions in images. Most existing methods use boundary maps to learn the sharp boundary. These methods ignore the interaction…

DecoderObjectobject-detectionObject Detection+3

Selectivity or Invariance: Boundary-aware Salient Object Detection

2018-12-25 · ICCV 2019 10 · Jinming Su, Jia Li, Yu Zhang, Changqun Xia 외

Typically, a salient object detection (SOD) model faces opposite requirements in processing object interiors and boundaries. The features of interiors should be invariant to strong appearance change so as to pop-out the …

Objectobject-detectionObject DetectionRGB Salient Object Detection+1