Personal robots and driverless cars need to be able to operate in novel environments and thus quickly and efficiently learn to recognise new object classes. We address this problem by considering the task of video object segmentation. Previous accurate methods for this task finetune a model using the first annotated frame, and/or use additional inputs such as optical flow and complex post-processing. In contrast, we develop a fast, causal algorithm that requires no finetuning, auxiliary inputs or post-processing, and segments a variable number of objects in a single forward-pass. We represent an object with clusters, or "visual words", in the embedding space, which correspond to object parts in the image space. This allows us to robustly match to the reference objects throughout the video, because although the global appearance of an object changes as it undergoes occlusions and deformations, the appearance of more local parts may stay consistent. We learn these visual words in an unsupervised manner, using meta-learning to ensure that our training objective matches our inference procedure. We achieve comparable accuracy to finetuning based methods (whilst being 1 to 2 orders of magnitude faster), and state-of-the-art in terms of speed/accuracy trade-offs on four video segmentation datasets. Code is available at https://github.com/harkiratbehl/MetaVOS.
Cascaded Segmentation-Detection Networks for Word-Level Text Spotting
University of California Santa Cruz(加州大学圣克鲁兹分校)
我们介绍了一种算法,字级的文本发现,能够准确可靠地确定文本的单个单词的边界区域“在野外”。我们的系统是由两个卷积神经网络级联而成。第一个网络是完全卷积的,负责检测包含文本的区域。这导致输入图像的非常可靠但可能不准确的分割。第二个网络(受流行的YOLO架构的启发)分析第一阶段产生的每个片段,并预测包含单个单词的定向矩形区域。不需要后处理(例如文本行分组)。在Titan X GPU上处理1000 x 560图像的执行时间为450 ms,我们的系统在ICDAR 2015 Incidental Scene Text数据集基准测试中获得了迄今为止已发布算法中的最高分数。
HMM-based Indic Handwritten Word Recognition using Zone Segmentation
Indian Institute of Technology Roorkee(印度理工学院鲁尔基分校);Institute of Engineering & Management, Kolkata(加尔各答工程与管理学院);Indian Statistical Institute, Kolkata(印度统计学院加尔各答分校)
Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation
University of Bonn, Germany(波恩大学);University College London, UK(伦敦大学学院);Lamarr Institute for Machine Learning and Artificial Intelligence, Germany(拉马尔人工智能与机器学习研究所)
WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image
University of Electronic Science and Technology of China(电子科技大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Sichuan Cancer Hospital and Institute(四川省肿瘤医院(四川省肿瘤研究所));Sichuan Cancer Center(四川省癌症中心);Sichuan University(四川大学);West China Hospital(华西医院);Johns Hopkins University(约翰斯·霍普金斯大学);SenseTime Research(商汤科技研究院);Rutgers University(罗格斯大学)
全腹腔器官分割在腹部病变诊断、放射治疗和随访中具有重要意义。然而,肿瘤学家从3D体积描绘所有腹部器官是耗时且非常昂贵的。基于深度学习的医学图像分割已经显示出减少人工描绘工作的潜力,但它仍然需要大规模的精细注释数据集进行训练,并且缺乏覆盖整个腹部区域的大规模数据集,这些数据集具有准确和详细的注释用于整个腹部器官分割。本工作建立了一个新的大规模\textit{W}孔腹\textit{OR} GAN \textit{D}子集(\textit{WORD}),用于算法研究和临床应用开发。该数据集包含150个腹部CT体积(30495个切片)。每个体积具有16个器官,具有精细像素级注释和基于潦草的稀疏注释,这可能是具有整个腹部器官注释的最大数据集。在此数据集上评估了几种最先进的分割方法。我们还邀请了三位经验丰富的肿瘤学家来修改模型预测,以衡量深度学习方法与肿瘤学家之间的差距。之后,我们研究了WORD上的推理高效学习,因为高分辨率图像需要大量的GPU内存和测试阶段的长推理时间。我们进一步评估了这个数据集上基于涂鸦的注释高效学习,因为像素级手动注释既耗时又昂贵。这项工作为腹部多器官分割任务提供了一个新的基准,这些实验可以作为未来研究和临床应用开发的基线。