Parametric PerceptNet：一种受生物启发的、用于图像质量评估的深度网络
Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment
AI总结：
本研究提出结合生物可信特性的参数化视觉模型Parametric PerceptNet，用于图像质量评估，在参数减少三个数量级的同时保持回归性能，还发现深度学习方法存在固有特征扩散问题。
摘要：
人类视觉模型是图像处理的核心。例如，图像质量问题的经典方法基于包含人类视觉相关知识的模型。然而如今，深度学习方法仅通过将该问题转化为人类决策的回归任务，并在人类评分数据集上训练标准网络，就取得了具有竞争力的结果。这类方法的优势在于易于适配特定问题，且在有数据可用时能高效拟合。但主要由于参数过多，它们存在可解释性不足和过拟合的问题。\n在此，我们提出一种视觉模型，通过使用参数化神经网络架构结合了两类方法的优势。我们将各层参数化以具备生物可信的功能，并提供了一组生物可信参数。我们分析了该模型的不同版本，并将其与非参数版本进行了对比。参数化模型实现了参数数量三个数量级的减少，且未损失回归性能。此外，我们表明参数化模型在训练过程中表现更优，且作为视觉模型更易于解释。\n有趣的是，我们发现，即便用针对人类评分数据集回归任务训练的生物可信参数初始化，仍会出现我们称之为特征扩散（feature-spreading）的问题。这表明深度学习方法存在固有缺陷，并强调了在回归之外评估和训练模型的必要性。
英文摘要：
Human vision models are at the core of image processing. For instance, classical approaches to the problem of image quality are based on models that include knowledge about human vision. However, nowadays, deep learning approaches have obtained competitive results by simply approaching this problem as regression of human decisions, and training an standard network on human-rated datasets. These approaches have the advantages of being easily adaptable to a particular problem and they fit very efficiently when data is available. However, mainly due to the excess of parameters, they have the problems of lack of interpretability, and over-fitting. Here we propose a vision model that combines the best of both worlds by using a parametric neural network architecture. We parameterize the layers to have bioplausible functionality, and provide a set of bioplausible parameters. We analyzed different versions of the model and compared it with the non-parametric version. The parametric models achieve a three orders of magnitude reduction in the number of parameters without suffering in regression performance. Furthermore, we show that the parametric models behave better during training and are easier to interpret as vision models. Interestingly, we find that, even initialized with bioplausible trained for regression using human rated datasets, which we call the feature-spreading problem. This suggests that the deep learning approach is inherently flawed, and emphasizes the need to evaluate and train models beyond regression.
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。
