论文标题

通过深编码的快速准确的光场显着性检测

Fast and Accurate Light Field Saliency Detection through Deep Encoding

论文作者

Hemachandra, Sahan, Rodrigo, Ranga, Edussooriya, Chamira

论文摘要

光场显着性检测 - 由于许多视觉任务的效用而重要 - 仍然缺乏速度,并且可以提高准确性。由于将显着性检测问题的提出为细分任务或记忆任务,因此现有方法可以消耗大量的培训计算资源,并具有更长的测试执行时间。我们通过将大型光场图像积极地减少到较小的三通道特征图中来解决此问题,该图形适用于使用带有注意机制的RGB图像显着探测器显着检测。我们通过引入一种新型的基于卷积神经网络的功能提取和编码模块来实现这一目标。我们的显着性检测器需要$ 0.4 $ S来处理CPU中的尺寸$ 9 \ TIMES9 \ TIMES9 \ TIMES512 \ TIMES375 $的光场,并且比最先进的光场显着探测器要快得多,精度更好或可比。此外,与最先进的光场显着探测器相比,我们体系结构的模型大小明显较低。我们的工作表明,通过攻击性尺寸降低从光场中提取特征,并且注意力机制可导致更快,准确的光场显着探测器,从而导致接近实时的光场处理。

Light field saliency detection -- important due to utility in many vision tasks -- still lacks speed and can improve in accuracy. Due to the formulation of the saliency detection problem in light fields as a segmentation task or a memorizing task, existing approaches consume unnecessarily large amounts of computational resources for training, and have longer execution times for testing. We solve this by aggressively reducing the large light field images to a much smaller three-channel feature map appropriate for saliency detection using an RGB image saliency detector with attention mechanisms. We achieve this by introducing a novel convolutional neural network based features extraction and encoding module. Our saliency detector takes $0.4$ s to process a light field of size $9\times9\times512\times375$ in a CPU and is significantly faster than state-of-the-art light field saliency detectors, with better or comparable accuracy. Furthermore, model size of our architecture is significantly lower compared to state-of-the-art light field saliency detectors. Our work shows that extracting features from light fields through aggressive size reduction and the attention mechanism results in a faster and accurate light field saliency detector leading to near real-time light field processing.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源