Face parsing is an important computer vision task that requires accurate pixel segmentation of facial parts (such as eyes, nose, mouth, etc.), providing a basis for further face analysis, modification, and other applications. Interlinked Convolutional Neural Networks (iCNN) was proved to be an effective two-stage model for face parsing. However, the original iCNN was trained separately in two stages, limiting its performance. To solve this problem, we introduce a simple, end-to-end face parsing framework: STN-aided iCNN(STN-iCNN), which extends the iCNN by adding a Spatial Transformer Network (STN) between the two isolated stages. The STN-iCNN uses the STN to provide a trainable connection to the original two-stage iCNN pipeline, making end-to-end joint training possible. Moreover, as a by-product, STN also provides more precise cropped parts than the original cropper. Due to these two advantages, our approach significantly improves the accuracy of the original model. Our model achieved competitive performance on the Helen Dataset, the standard face parsing dataset. It also achieved superior performance on CelebAMask-HQ dataset, proving its good generalization. Our code has been released at https://github.com/aod321/STN-iCNN.

人脸解析是一项重要的计算机视觉任务，需要对人脸部位（如眼睛、鼻子、嘴巴等）进行精确的像素分割，为进一步的人脸分析、修饰等应用提供基础。互连卷积神经网络（iCNN）被证明是一种有效的人脸解析两阶段模型。然而，最初的 iCNN 是分两个阶段单独训练的，限制了其性能。为了解决这个问题，我们引入了一个简单的端到端人脸解析框架：STN辅助iCNN（STN-iCNN），它通过在两个隔离阶段之间添加空间变换网络（STN）来扩展iCNN。 STN-iCNN 使用 STN 提供与原始两级 iCNN 管道的可训练连接，使端到端联合训练成为可能。此外，作为副产品，STN 还提供比原始裁剪器更精确的裁剪部分。由于这两个优点，我们的方法显着提高了原始模型的准确性。我们的模型在标准人脸解析数据集 Helen 数据集上取得了有竞争力的性能。它还在 CelebAMask-HQ 数据集上取得了优异的性能，证明了其良好的泛化性。我们的代码已发布在 https://github.com/aod321/STN-iCNN。