Showing papers by "Charles R. Dyer published in 2016"

Efficient Branching Cascaded Regression for Face Alignment under Significant Head Rotation.

Abstract: Despite much interest in face alignment in recent years, the large majority of work has focused on near-frontal faces. Algorithms typically break down on profile faces, or are too slow for real-time applications. In this work we propose an efficient approach to face alignment that can handle 180 degrees of head rotation in a unified way (e.g., without resorting to view-based models) using 2D training data. The foundation of our approach is cascaded shape regression (CSR), which has emerged recently as the leading strategy. We propose a generalization of conventional CSRs that we call branching cascaded regression (BCR). Conventional CSRs are single-track; that is, they progress from one cascade level to the next in a straight line, with each regressor attempting to fit the entire dataset. We instead split the regression problem into two or more simpler ones after each cascade level. Intuitively, each regressor can then operate on a simpler objective function (i.e., with fewer conflicting gradient directions). Within the BCR framework, we model and infer pose-related landmark visibility and face shape simultaneously using Structured Point Distribution Models (SPDMs). We propose to learn task-specific feature mapping functions that are adaptive to landmark visibility, and that use SPDM parameters as regression targets instead of 2D landmark coordinates. Additionally, we introduce a new in-the-wild dataset of profile faces to validate our approach.

Abundant Inverse Regression Using Sufficient Reduction and Its Applications

Abstract: Statistical models such as linear regression drive numerous applications in computer vision and machine learning. The landscape of practical deployments of these formulations is dominated by forward regression models that estimate the parameters of a function mapping a set of p covariates, \(\varvec{x}\), to a response variable, y. The less known alternative, Inverse Regression, offers various benefits that are much less explored in vision problems. The goal of this paper is to show how Inverse Regression in the “abundant” feature setting (i.e., many subsets of features are associated with the target label or response, as is the case for images), together with a statistical construction called Sufficient Reduction, yields highly flexible models that are a natural fit for model estimation tasks in vision. Specifically, we obtain formulations that provide relevance of individual covariates used in prediction, at the level of specific examples/samples — in a sense, explaining why a particular prediction was made. With no compromise in performance relative to other methods, an ability to interpret why a learning algorithm is behaving in a specific way for each prediction, adds significant value in numerous applications. We illustrate these properties and the benefits of Abundant Inverse Regression on three distinct applications.

Pose-Robust 3D Facial Landmark Estimation from a Single 2D Image.

Abstract: An algorithm is presented that estimates 3D facial landmark coordinates and occlusion state from a single 2D image. Unlike previous approaches, we divide the 3D cascaded shape regression problem into a set of viewpoint domains, which helps avoid problems in the optimization, such as local minima at test time, and averaging conflicting gradient directions in the domain maps during training. These problems are especially important to address in the 3D case, where a wider range of head poses is expected. Parametric shape models are used and are shown to have several desirable qualities compared to the recent trend of modeling shape nonparametrically. Results show quantitatively that our approach is significantly more accurate than recent work.