通过运动与物体连续性提升物体表示学习
Boosting Object Representation Learning via Motion and Object Continuity
AI总结：
本文提出MOC方案，通过光流位置先验和跨帧对比连续性损失，利用运动与物体连续性提升无监督多物体检测模型的物体表示质量，在Atari游戏等下游任务中显著改善物体发现、收敛速度与潜在表示。
摘要：
近期无监督多物体检测模型展现出显著的性能提升，这主要归因于新颖的架构归纳偏置。然而，这些模型可能为下游任务生成次优的物体编码。为克服这一问题，我们提出利用物体运动与连续性，即物体不会突然出现或消失。这通过两种机制实现：（i）通过整合光流为物体位置提供先验；（ii）在连续图像帧之间引入对比式物体连续性损失。所提出的运动与物体连续性（MOC）方案无需开发显式的深度架构，可使用任何基线物体检测模型进行实例化。我们的结果表明，在物体发现、收敛速度和整体潜在物体表示方面，SOTA模型的性能均有大幅提升，尤其是在玩Atari游戏时。总体而言，我们展示了将运动与物体连续性整合用于下游任务的明显优势，超越了仅基于重建的物体表示学习。
英文摘要：
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they may produce suboptimal object encodings for downstream tasks. To overcome this, we propose to exploit object motion and continuity, i.e., objects do not pop in and out of existence. This is accomplished through two mechanisms: (i) providing priors on the location of objects through integration of optical flow, and (ii) a contrastive object continuity loss across consecutive image frames. Rather than developing an explicit deep architecture, the resulting Motion and Object Continuity (MOC) scheme can be instantiated using any baseline object detection model. Our results show large improvements in the performances of a SOTA model in terms of object discovery, convergence speed and overall latent object representations, particularly for playing Atari games. Overall, we show clear benefits of integrating motion and object continuity for downstream tasks, moving beyond object representation learning based only on reconstruction.
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。
