Interlinked Convolutional Neural Networks for Face Parsing

TL;DR

This paper introduces an interlinked convolutional neural network (iCNN) architecture that effectively combines multi-scale features for precise face parsing, achieving superior results on benchmark datasets.

Contribution

The paper proposes a novel iCNN architecture with interlinking layers that exchange information across scales, enhancing face parsing performance in an end-to-end framework.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Utilizes extensive downsampling and upsampling in interlinking layers.

Employs a two-stage pipeline for face parsing with improved accuracy.

Abstract

Face parsing is a basic task in face image analysis. It amounts to labeling each pixel with appropriate facial parts such as eyes and nose. In the paper, we present a interlinked convolutional neural network (iCNN) for solving this problem in an end-to-end fashion. It consists of multiple convolutional neural networks (CNNs) taking input in different scales. A special interlinking layer is designed to allow the CNNs to exchange information, enabling them to integrate local and contextual information efficiently. The hallmark of iCNN is the extensive use of downsampling and upsampling in the interlinking layers, while traditional CNNs usually uses downsampling only. A two-stage pipeline is proposed for face parsing and both stages use iCNN. The first stage localizes facial parts in the size-reduced image and the second stage labels the pixels in the identified facial parts in the original image. On a benchmark dataset we have obtained better results than the state-of-the-art methods.