参考链接:https://zhuanlan.zhihu.com/p/109644739
同步公众号(arXiv每日学术速递)
[检测分类相关]:
【1】 2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification
二维卷积神经网络用于三维数字乳腺断层合成分类
作者: Yu Zhang, Nathan Jacobs
备注:Accepted by IEEE International Conference of Bioinformatics and Biomedicine (BIBM), 2019
链接:https://arxiv.org/abs/2002.12314

【2】 The Data Representativeness Criterion: Predicting the Performance of Supervised Classification Based on Data Set Similarity
数据代表性准则:基于数据集相似度的监督分类性能预测
作者: Evelien Schat, Adriënne M. Mendrik
链接:https://arxiv.org/abs/2002.12105

【3】 Two-stage breast mass detection and segmentation system towards automated high-resolution full mammogram analysis
面向自动化高分辨率全乳房X光分析的两阶段乳腺肿块检测和分割系统
作者: Yutong Yan, Gouenou Coatrieux
链接:https://arxiv.org/abs/2002.12079

【4】 Comparison of Multi-Class and Binary Classification Machine Learning Models in Identifying Strong Gravitational Lenses
多分类和二元分类机器学习模型在强引力透镜识别中的比较
作者: Hossen Teimoorinia, Connor Bottrell
链接:https://arxiv.org/abs/2002.11849

[分割/语义相关]:
【1】 Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
语义引导的自监督单目深度表征学习
作者: Vitor Guizilini, Adrien Gaidon
备注:Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020)
链接:https://arxiv.org/abs/2002.12319

【2】 Attention-guided Chained Context Aggregation for Semantic Segmentation
用于语义分割的注意力引导的链式上下文聚合
作者: Quan Tang, Yu Zhang
链接:https://arxiv.org/abs/2002.12041

【3】 Set-Constrained Viterbi for Set-Supervised Action Segmentation
集合约束的维特比集合监督行为分割
作者: Jun Li, Sinisa Todorovic
链接:https://arxiv.org/abs/2002.11925

【4】 Coronary Wall Segmentation in CCTA Scans via a Hybrid Net with Contours Regularization
基于轮廓正则化的混合网络在CCTA扫描中的冠状动脉壁分割
作者: Kaikai Huang, Tatsuya Harada
备注:5 pages, 2 figures, accepted by ISBI 2020
链接:https://arxiv.org/abs/2002.12263

【5】 Segmentation-based Method combined with Dynamic Programming for Brain Midline Delineation
基于分割与动态规划相结合的脑中线划分方法
作者: Shen Wang, Yizhou Wang
链接:https://arxiv.org/abs/2002.1191
[其他]:
【1】 Rethinking the Hyperparameters for Fine-tuning
对微调超参数的再思考
作者: Hao Li, Stefano Soatto
备注:Published as a conference paper at ICLR 2020
链接:https://arxiv.org/abs/2002.1177

Logo

魔乐社区(Modelers.cn) 是一个中立、公益的人工智能社区,提供人工智能工具、模型、数据的托管、展示与应用协同服务,为人工智能开发及爱好者搭建开放的学习交流平台。社区通过理事会方式运作,由全产业链共同建设、共同运营、共同享有,推动国产AI生态繁荣发展。

更多推荐