Behavior of neural networks is irremediably determined by the specific loss and data used during training. However it is often desirable to tune the model at inference time based on external factors such as preferences of the user or dynamic characteristics of the data. This is especially important to balance the perception-distortion trade-off of ill-posed image-to-image translation tasks. In this work, we propose to optimize a parametric tunable convolutional layer, which includes a number of different kernels, using a parametric multi-loss, which includes an equal number of objectives. Our key insight is to use a shared set of parameters to dynamically interpolate both the objectives and the kernels. During training, these parameters are sampled at random to explicitly optimize all possible combinations of objectives and consequently disentangle their effect into the corresponding kernels. During inference, these parameters become interactive inputs of the model hence enabling reliable and consistent control over the model behavior. Extensive experimental results demonstrate that our tunable convolutions effectively work as a drop-in replacement for traditional convolutions in existing neural networks at virtually no extra computational cost, outperforming state-of-the-art control strategies in a wide range of applications; including image denoising, deblurring, super-resolution, and style transfer.
翻译:神经网络的行为决定于特定的损失和训练数据。然而,通过外部因素对模型进行调整,例如用户偏好或数据的动态特性,尤其重要。这对于平衡病态图像转换任务的感知-失真权衡尤其重要。在本文中,我们提出使用参数化的可调卷积层,并使用参数化的多目标来优化该层, 该层包含多个不同的卷积核,多目标包括相同数量的目标。我们的关键见解是使用共享的参数,动态插值目标和卷积核。在训练期间,这些参数被随机取样以显式优化所有可能的目标组合,并将其作用拆分到相应的卷积核。在推断期间,这些参数成为模型的交互输入,从而实现对模型行为的可靠和一致的控制。广泛的实验结果表明,在几乎没有额外计算成本的情况下,我们的可调卷积有效地作为传统卷积在现有神经网络中的替代,优于当前最先进的控制策略,在各种应用中都表现出色,包括图像去噪、去模糊、超分辨率和风格迁移。<br>