arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1812.01397cs.CV
收藏

Meta学习深度视觉词用于快速视频对象分割

Meta Learning Deep Visual Words for Fast Video Object Segmentation

University of Oxford(牛津大学);Google Research(谷歌研究院)

Harkirat Singh Behl, Mohammad Najafi, Anurag Arnab, Philip H. S. Torr

摘要:

个人机器人和无人驾驶汽车需要能够在新的环境中运行,从而快速有效地学习识别新的对象类别。我们通过考虑视频对象分割的任务来解决这个问题。用于该任务的先前精确方法使用第一注释帧微调模型,和/或使用诸如光流和复杂的后处理的附加输入。相比之下,我们开发了一个快速的因果算法,不需要微调,辅助输入或后处理,并在一个单一的前向传递中分割可变数量的对象。我们在嵌入空间中用聚类或“视觉词”表示对象,这些聚类或“视觉词”对应于图像空间中的对象部分。这使我们能够在整个视频中与参考对象进行鲁棒匹配,因为尽管对象的全局外观会随着遮挡和变形而变化,但更多局部部分的外观可能会保持一致。我们以无监督的方式学习这些视觉词汇,使用元学习来确保我们的训练目标与我们的推理过程相匹配。我们实现了与基于微调的方法相当的准确性(同时快1到2个数量级),并且在四个视频分割数据集上的速度/准确性权衡方面达到了最先进的水平。代码可在https://github.com/harkiratbehl/MetaVOS上获得。

英文摘要:

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.

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。

↑