arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.28771cs.LGcs.CV
收藏

运动等变卷积LSTM:当运动成为规范对称性

Motion Equivariant Convolutional LSTM: When Motion Becomes a Gauge Symmetry

South Dakota State University(南达科他州立大学);The Kempner Institute at Harvard University(哈佛大学坎普纳研究所);Cusp AI;Department of Mathematics & Statistics(数学与统计系)

Vahid Hosseinzadeh, T. Anderson Keller, Michael Puthawala

AI总结:

该研究提出运动等变卷积LSTM(MELSTM),将运动视为规范对称性,扩展流等变思路到卷积LSTM、时变运动和速度估计,在三类任务中性能优于同类模型。

摘要:

物体移动、相机平移、天气随风漂移:时序数据中发生变化的大多是运动。运动改变的是事物的位置而非属性,因此是数据的一种对称性。然而标准循环网络对运动并不等变:其记忆保持固定,而输入却在移动。流等变循环网络首次将这种对称性引入序列模型,针对恒定速度的运动(即流),通过枚举一组速度实现。我们从三个方向扩展了这一思路:从简单循环网络扩展到卷积LSTM,从流扩展到速度随时间变化的运动,从枚举速度扩展到估计速度。将序列视为时间上的场,我们证明运动成为一种规范对称性:一种在时间上局部化的全局对称性。基于这一观点,我们的运动等变卷积LSTM(MELSTM)将其速度模型用作规范场,且对所有运动都具有可证明的等变性。在未来帧预测、仅通过运动可见的数字分类以及相机抖动下的动作识别任务中,MELSTM在参数数量相同的情况下,性能优于卷积LSTM及其流等变对应模型:它更准确,能泛化到更长的时间范围和未见过的运动,且仅占用流等变模型一小部分的状态。

英文摘要:

Objects move, cameras pan, and weather drifts with the wind: much of what changes in sequential data is motion. Motion changes where things are, not what they are, and is therefore a symmetry of the data. Yet standard recurrent networks are not equivariant to it: their memory stays put while the input moves on. Flow equivariant recurrent networks first brought this symmetry into sequence models, for motions of constant velocity, or flows, by enumerating a bank of velocities. We extend this idea in three directions: from simple recurrent networks to convolutional LSTMs, from flows to motions whose velocity changes in time, and from enumerating velocities to estimating them. Treating a sequence as a field over time, we show that motion becomes a gauge symmetry: a global symmetry made local in time. Built on this view, our motion equivariant convolutional LSTM (MELSTM) uses its velocity model as the gauge field and is provably equivariant to every motion. Across future-frame prediction, classification of digits visible only through their motion, and action recognition under camera shake, MELSTM outperforms a convolutional LSTM and its flow equivariant counterpart with the same number of parameters: it is more accurate, generalizes to longer horizons and to unseen motions, and carries a fraction of the flow equivariant model's state.

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。

↑