一种面向心理物理学的显著性图预测模型
A Psychophysically Oriented Saliency Map Prediction Model
AI总结：
本研究受人类视觉皮层多通道机制启发，提出心理物理学显著性预测架构WECSF，在多类数据集上性能优于多数先进模型，可为灵长类视觉机制研究提供计算模型支撑。
摘要：
视觉注意力是人类筛选和理解冗余外部世界的核心特征之一。由于视觉信息瓶颈的存在，人类视觉系统无法同时处理所有信息。为减少视觉信息的冗余输入，人类视觉系统主要聚焦于场景中的主导区域，这一领域通常被称为视觉显著性图预测。本文受人类视觉皮层多通道功能模型启发，提出了一种全新的心理物理学显著性预测架构WECSF。该模型由对立色通道、小波变换、小波能量图和对比敏感度函数组成，用于提取低层图像特征，最大程度地模拟人类视觉系统的工作机制。研究使用多个数据集对所提模型进行评估，包括MIT1003、MIT300、TORONTO、SID4VAM和UCF Sports数据集，并从定量和定性两方面将其显著性预测性能与其他主流的先进模型进行对比。结果显示，该模型在自然图像、心理物理学合成图像和动态视频上，通过不同评价指标均取得了稳定且更优的性能。此外，研究发现基于傅里叶和频谱的显著性预测模型在心理物理学合成图像上的表现，优于其他先进的非神经网络模型甚至深度神经网络模型，这一现象可由傅里叶视觉假说解释和支撑。同时研究指出，深度神经网络需要特定的架构与目标，才能更优、更可靠地预测心理物理学合成图像上的显著性表现。最后，该模型可作为灵长类视觉系统的计算模型，帮助研究者理解灵长类视觉系统的工作机制。
英文摘要：
Visual attention is one of the most significant characteristics for selecting and understanding the outside redundancy world. The human vision system cannot process all information simultaneously due to the visual information bottleneck. In order to reduce the redundant input of visual information, the human visual system mainly focuses on dominant parts of scenes. This is commonly known as visual saliency map prediction. This paper proposed a new psychophysical saliency prediction architecture, WECSF, inspired by multi-channel model of visual cortex functioning in humans. The model consists of opponent color channels, wavelet transform, wavelet energy map, and contrast sensitivity function for extracting low-level image features and providing a maximum approximation to the human visual system. The proposed model is evaluated using several datasets, including the MIT1003, MIT300, TORONTO, SID4VAM, and UCF Sports datasets. We also quantitatively and qualitatively compare the saliency prediction performance with that of other state-of-the-art models. Our model achieved strongly stable and better performance with different metrics on natural images, psychophysical synthetic images and dynamic videos. Additionally, we found that Fourier and spectral-inspired saliency prediction models outperformed other state-of-the-art non-neural network and even deep neural network models on psychophysical synthetic images. It can be explained and supported by the Fourier Vision Hypothesis. In the meantime, we suggest that deep neural networks need specific architectures and goals to be able to predict salient performance on psychophysical synthetic images better and more reliably. Finally, the proposed model could be used as a computational model of primate vision system and help us understand mechanism of primate vision system.
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。
