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 2104.00177cs.CV
收藏

想象主体的视觉注意

Visual Attention in Imaginative Agents

McGill University(麦吉尔大学)

Samrudhdhi B. Rangrej, James J. Clark

摘要:

我们提出了一个经常性的代理人通过一系列离散的固定感知周围环境。在每一个时间步,智能体都想象出与注视历史相一致的各种似是而非的场景。下一个固定计划使用想象场景内容的不确定性。随着时间的推移,代理人变得更加确定周围的内容,想象场景的多样性减少。该代理是建立使用变分自编码器和规范化流程,并在一个场景重建的代理任务的无监督的方式进行训练。想象场景的潜在表征被发现是有用的高阶模块执行像素级和场景级的任务。该代理在各种2D和3D数据集上进行测试。

英文摘要:

We present a recurrent agent who perceives surroundings through a series of discrete fixations. At each timestep, the agent imagines a variety of plausible scenes consistent with the fixation history. The next fixation is planned using uncertainty in the content of the imagined scenes. As time progresses, the agent becomes more certain about the content of the surrounding, and the variety in the imagined scenes reduces. The agent is built using a variational autoencoder and normalizing flows, and trained in an unsupervised manner on a proxy task of scene-reconstruction. The latent representations of the imagined scenes are found to be useful for performing pixel-level and scene-level tasks by higher-order modules. The agent is tested on various 2D and 3D datasets.

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。

↑