AdaGlimpse:具备任意瞥见位置与尺度的主动视觉探索
AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale
AI总结:
针对现有主动视觉探索方法受限于固定尺度刚性网格、与移动平台光学变焦硬件能力不匹配的问题,提出基于Soft Actor-Critic强化学习的AdaGlimpse方法,可选择任意位置和尺度的瞥见,在多视觉任务上性能更优且真实场景适用性更强。
摘要:
主动视觉探索(AVE)是一项涉及动态选择观测结果(瞥见)的任务,对提升环境中的理解与导航能力至关重要。尽管现代AVE方法已展现出优异性能,但它们受限于刚性网格上的固定尺度瞥见。相比之下,现有配备光学变焦功能的移动平台可捕获任意位置和尺度的瞥见。为填补软件与硬件能力之间的这一差距,我们提出AdaGlimpse。它采用专为探索任务定制的强化学习算法Soft Actor-Critic,来选择任意位置和尺度的瞥见。该方法使我们的模型能够先快速建立对环境的整体感知,再放大进行细节分析。实验结果表明,AdaGlimpse在各类视觉任务上均优于现有方法,同时在真实AVE场景中具备更强的适用性。
英文摘要:
Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment. While modern AVE methods have demonstrated impressive performance, they are constrained to fixed-scale glimpses from rigid grids. In contrast, existing mobile platforms equipped with optical zoom capabilities can capture glimpses of arbitrary positions and scales. To address this gap between software and hardware capabilities, we introduce AdaGlimpse. It uses Soft Actor-Critic, a reinforcement learning algorithm tailored for exploration tasks, to select glimpses of arbitrary position and scale. This approach enables our model to rapidly establish a general awareness of the environment before zooming in for detailed analysis. Experimental results demonstrate that AdaGlimpse surpasses previous methods across various visual tasks while maintaining greater applicability in realistic AVE scenarios.
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。