Contextually Guided Convolutional Neural Networks for Learning Most Transferable Representations
Contextually Guided Convolutional Neural Networks for Learning Most Transferable Representations
复制标题
DOI：
10.1109/ism55400.2022.00047
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Olcay Kursun;S. Dinç;O. Favorov
中科院分区：
文献类型：
--
作者：
Olcay Kursun;S. Dinç;O. Favorov
通过在单层CNN结构中实现局部上下文指导原则，我们提出了一种高效的算法，用于在有限大小的数据集上训练的浅层CNN中开发通用表示(即，无需额外训练即可转移到新任务的表示)。上下文制导的CNN(CG-CNN)针对在数据集中的随机图像位置拾取的相邻图像块组进行训练。这种相邻的补丁可能具有共同的背景，因此出于训练的目的被视为属于同一类。在对不同的上下文共享图像块组的这种训练的多次迭代中，在一次迭代中优化的CNN特征然后被转移到下一次迭代以进行进一步的优化，等等。在这个过程中，CNN特征获得了更高的多能性，或者对于任意分类任务的推论效用。在我们对自然图像和高光谱图像的应用中，我们发现CG-CNN可以学习到类似于众所周知的深层网络第一层学习的可转移特征，并产生良好的分类精度。
Implementing local contextual guidance principles in a single-layer CNN architecture, we propose an efficient algorithm for developing broad-purpose representations (i.e., representations transferable to new tasks without additional training) in shallow CNNs trained on limited-size datasets. A contextually guided CNN (CG-CNN) is trained on groups of neighboring image patches picked at random image locations in the dataset. Such neighboring patches are likely to have a common context and therefore are treated for the purposes of training as belonging to the same class. Across multiple iterations of such training on different context-sharing groups of image patches, CNN features that are optimized in one iteration are then transferred to the next iteration for further optimization, etc. In this process, CNN features acquire higher pluripotency, or inferential utility for any arbitrary classification task. In our applications to natural images and hyperspectral images, we find that CG-CNN can learn transferable features similar to those learned by the first layers of the well-known deep networks and produce favorable classification accuracies.