首页/论文/2005.09007

arXiv 2005.090072022-03-08cs.CV

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

University of Alberta（阿尔伯塔大学）

Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane, Martin Jagersand

备注：: Accepted in Pattern Recognition 2020
DOI：: 10.1016/j.patcog.2020.107404

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U$^2$-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U$^2$-Net$^{\dagger}$ (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images

City University of Hong Kong（香港城市大学）；Beijing Jiaotong University（北京交通大学）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）；Tianjin University（天津大学）

Arising from the various object types and scales, diverse imaging orientations, and cluttered backgrounds in optical remote sensing image (RSI), it is difficult to directly extend the success of salient object detection for nature scene image to the optical RSI. In this paper, we propose an end-to-end deep network called LV-Net based on the shape of network architecture, which detects salient objects from optical RSIs in a purely data-driven fashion. The proposed LV-Net consists of two key modules, i.e., a two-stream pyramid module (L-shaped module) and an encoder-decoder module with nested co…

2019-06-20cs.CV

U$^2$Mamba：用于显著目标检测的两级嵌套U结构Mamba

U$^2$Mamba: A Two-level Nested U-structure Mamba for Salient Object Detection

University of Science and Technology Liaoning（辽宁科技大学）；Chuzhou University（滁州学院）；Yeshiva University（叶史瓦大学）

提出U$^2$Mamba，一种两级嵌套U结构网络，通过多尺度Mamba U块增强深度和上下文信息，并采用分层训练监督，在显著目标检测上达到先进性能。

2026-06-19cs.CV

Densely Nested Top-Down Flows for Salient Object Detection

School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；School of Mechano-Electronic Engineering, Xidian University（西安电子科技大学机电工程学院）；Aberystwyth University（阿伯里斯特威斯大学）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）

With the goal of identifying pixel-wise salient object regions from each input image, salient object detection (SOD) has been receiving great attention in recent years. One kind of mainstream SOD methods is formed by a bottom-up feature encoding procedure and a top-down information decoding procedure. While numerous approaches have explored the bottom-up feature extraction for this task, the design on top-down flows still remains under-studied. To this end, this paper revisits the role of top-down modeling in salient object detection and designs a novel densely nested top-down flows (DNTDF)-ba…

2021-02-18cs.CV

M2RNet: Multi-modal and Multi-scale Refined Network for RGB-D Salient Object Detection

Nankai University（南开大学）；Peking University（北京大学）

Salient object detection is a fundamental topic in computer vision. Previous methods based on RGB-D often suffer from the incompatibility of multi-modal feature fusion and the insufficiency of multi-scale feature aggregation. To tackle these two dilemmas, we propose a novel multi-modal and multi-scale refined network (M2RNet). Three essential components are presented in this network. The nested dual attention module (NDAM) explicitly exploits the combined features of RGB and depth flows. The adjacent interactive aggregation module (AIAM) gradually integrates the neighbor features of high, midd…

2021-09-16cs.CV

Deeply supervised salient object detection with short connections

Nankai University（南开大学）；University of Central Florida（中佛罗里达大学）；University of California at San Diego（加利福尼亚大学圣地亚哥分校）；University of Oxford（牛津大学）

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…

2018-03-16cs.CV

DC-Net：用于显著性目标检测的分而治之方法

DC-Net: Divide-and-Conquer for Salient Object Detection

MBZUAI（穆罕默德·本·扎耶德人工智能大学）

本文将分而治之策略引入显著性目标检测，提出DC-Net，通过双编码器处理边缘与位置预测子任务，并利用两级残差嵌套ASPP模块聚合特征，在保持高效率的同时于多个数据集上取得竞争力。

2024-01-10cs.CV

更多相关论文收起更多论文

重新思考RGB-D显著目标检测：模型、数据集与大规模基准

Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks

College of Computer Science, Nankai University（南开大学计算机学院）；Google AI（谷歌人工智能）

本文针对真实场景RGB-D显著目标检测，构建了SIP显著人物数据集和大规模基准，并提出深度净化网络D3Net，在多项指标上超越现有方法并支持高效背景替换。

2020-07-11cs.CV

SiaTrans: Siamese Transformer Network for RGB-D Salient Object Detection with Depth Image Classification

Shandong University of Science and Technology（山东科技大学）

RGB-D SOD uses depth information to handle challenging scenes and obtain high-quality saliency maps. Existing state-of-the-art RGB-D saliency detection methods overwhelmingly rely on the strategy of directly fusing depth information. Although these methods improve the accuracy of saliency prediction through various cross-modality fusion strategies, misinformation provided by some poor-quality depth images can affect the saliency prediction result. To address this issue, a novel RGB-D salient object detection model (SiaTrans) is proposed in this paper, which allows training on depth image quali…

2022-07-09cs.CVcs.LG

Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling

University of Trento（特伦托大学）；ETH Zurich（苏黎世联邦理工学院）

Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed all of which rely on the contour/edge information to improve detection performance. The edge labels are either put into the loss directly or used as extra supervision. The edge and body can also be learned separately and then fused afterward. Both methods either lead to high prediction errors near the edge or cannot be trained in an end-to-end manner. Another problem is that existing methods may fail to detect objects of v…

2022-02-08cs.CV

Nested Grassmannians for Dimensionality Reduction with Applications

National Taiwan University（台湾大学）；University of Florida（佛罗里达大学）

In the recent past, nested structures in Riemannian manifolds has been studied in the context of dimensionality reduction as an alternative to the popular principal geodesic analysis (PGA) technique, for example, the principal nested spheres. In this paper, we propose a novel framework for constructing a nested sequence of homogeneous Riemannian manifolds. Common examples of homogeneous Riemannian manifolds include the $n$-sphere, the Stiefel manifold, the Grassmann manifold and many others. In particular, we focus on applying the proposed framework to the Grassmann manifold, giving rise to th…

2022-03-01cs.CVstat.ME

Hierarchical multi-class segmentation of glioma images using networks with multi-level activation function

Technische Universität München（慕尼黑工业大学）

For many segmentation tasks, especially for the biomedical image, the topological prior is vital information which is useful to exploit. The containment/nesting is a typical inter-class geometric relationship. In the MICCAI Brain tumor segmentation challenge, with its three hierarchically nested classes 'whole tumor', 'tumor core', 'active tumor', the nested classes relationship is introduced into the 3D-residual-Unet architecture. The network comprises a context aggregation pathway and a localization pathway, which encodes increasingly abstract representation of the input as going deeper into…

2018-11-02cs.CV