通过放宽共同命运与视觉分组从视频中自举物体性
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
AI总结：
本文提出从无标注视频中自举物体性的方法：先用放宽的共同命运学习特征，再通过图像内和跨图像的外观分组统计精炼，在无监督视频物体分割上超越现有方法。
摘要：
我们研究从未标注视频中学习物体分割。人类能够轻松分割运动物体，即使不知道它们是什么。格式塔共同命运定律——即以相同速度运动的物体属于同一整体——启发了基于运动分割的无监督物体发现。然而，共同命运并不是物体性的可靠指标：铰接式或可变形物体的各个部分可能不以相同速度运动，而物体的阴影或反射总是随其运动但并不属于物体本身。我们的洞见是：首先从放宽的共同命运中学习图像特征，然后基于图像内部以及跨图像的视觉外观分组统计地对其进行精炼，从而自举物体性。具体来说，我们先在以下循环中学习图像分割器：用恒定分割流加上小的分割内残差流来近似光流，然后通过精炼使其具有更一致的外观和统计上的图形-背景相关性。在无监督视频物体分割任务上，仅使用ResNet和卷积头，我们的模型在DAVIS16 / STv2 / FBMS59上分别以7/9/5%的绝对增益超越了最先进方法，证明了我们思路的有效性。我们的代码已公开。
英文摘要：
We study learning object segmentation from unlabeled videos. Humans can easily segment moving objects without knowing what they are. The Gestalt law of common fate, i.e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation. However, common fate is not a reliable indicator of objectness: Parts of an articulated / deformable object may not move at the same speed, whereas shadows / reflections of an object always move with it but are not part of it. Our insight is to bootstrap objectness by first learning image features from relaxed common fate and then refining them based on visual appearance grouping within the image itself and across images statistically. Specifically, we learn an image segmenter first in the loop of approximating optical flow with constant segment flow plus small within-segment residual flow, and then by refining it for more coherent appearance and statistical figure-ground relevance. On unsupervised video object segmentation, using only ResNet and convolutional heads, our model surpasses the state-of-the-art by absolute gains of 7/9/5% on DAVIS16 / STv2 / FBMS59 respectively, demonstrating the effectiveness of our ideas. Our code is publicly available.
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。
