.png){kind=icon}
返回
Benchmarking deep models on salient object detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109951.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The performance discrepancies caused by different implementation details may obscure the actual progress of the Salient Object Detection (SOD) task. In this paper, we construct a SALient Object Detection (SALOD) benchmark to ensure a fair and comprehensive evaluation by unifying the implementation details of SOD methods. By doing so, we can reveal the reasons behind recent progress by analyzing the impact of network structure and optimization strategy. Based on the experimental results, we first find that U-shaped networks, both older and more recent variants, achieve better performance than other structures. Second, optimization strategy, e.g., training strategy and loss function, significantly impacts SOD accuracy. Finally, we provide a new perspective to validate the generalizability of SOD methods on objectness shifting. Code is available at https://github.com/moothes/SALOD.
Keyword:
Benchmark
Salient object detection
Loss function
Objectness
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Molecular and Pharmacological Characterization of GABAA Receptors in the Rat Pituitary大鼠垂体中GABAA 受体的分子和药理学特征
PREAI
分享收藏LID, LEED, and Alternative Rating Systems—Integrating Low Impact Development Techniques with Green Building DesignLID，LEED和替代评级系统-将低影响开发技术与绿色建筑设计相结合
PREAI
分享收藏Distribution, Source Identification, and Assessment of Potentially Toxic Elements in the Sediment Core from the Estuarine Region of the Golmud River to the Qarhan Salt Lake, Qinghai, China.png)
MineralsOAAI
MineralsIF0
OAAI分享收藏Saliency for fine-grained object recognition in domains with scarce training dataPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Contour-Aware Loss: Boundary-Aware Learning for Salient Object Segmentation轮廓感知损失: 用于显着对象分割的边界感知学习
PREAI
分享收藏
查看更多内容