Facial Landmark Detection by Deep Multi-task Learning

By Zhanpeng Zhang, Ping Luo, Chen Change Loy, Xiaoou Tang. 2014

1,538 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Dermatology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Dermatology

Citations in the corpus

An Overview of Multi-task Learning (2018, background): “Specifically, applications of MTL based on facial images include face verification [84], personalized age estimation [85], multi-cue face recognition [86], head-pose estimation [22,87], facial landmark detection [18], and facial image rotation [88].”
Learning multiple visual domains with residual adapters (2017, methodology): “MTL in DNNs has been applied to various problems ranging from natural language processing [8, 22], speech recognition [14] to computer vision [41, 42, 4].”
Cross-Stitch Networks for Multi-task Learning (2016, background): “pose estimation and action recognition [22], surface normals and edge labels [52], face landmark detection and face detection [57, 59], auxiliary tasks in detection [21], related”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “…[14, 27,67], region proposal generation [30,82,85], instance segmentation [21, 37, 82], pose estimation, part segmentation, and landmark localization [3,15,42,75,81,96,98,104,111], as well as the large body of works around object detection and image classiﬁcation e.g. [22,31,32,40,52,85,89,93,94].”
One Model To Learn Them All (2017, methodology): “-shot learning when trained on multiple langauges [18]. Speech recognition has also been shown to beneﬁt from multi-task training [24], as have some vision problems, such as facial landmark detection [31]. But all these models are trained on other tasks from the same domain: translation tasks are tr”
A Survey on Multi-Task Learning (2017, methodology): “1, many deep MTL methods [17], [18], [19], [20], [21] assume that different tasks share the first several hidden layers and then have task-specific parameters in the subsequent layers.”
Efficient Parametrization of Multi-domain Deep Neural Networks (2018, methodology): “In computer vision, deep MTL models are applied to object tracking [34], facial-landmark detection [35], object and part detection [2], object detection and instance segmentation [10], a collection of low-level and high-level vision tasks [14].”
Gradient Surgery for Multi-Task Learning (2020, methodology): “The multi-task formulation has been applied to many different settings, including supervised learning (Zhang et al., 2014; Long & Wang, 2015; Yang & Hospedales, 2016; Sener & Koltun, 2018; Zamir et al., 2018) and reinforcement-learning (Espeholt et al.”
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks (2017, background): “Please refer to the Supplementary Materials for additional results on a 9-task facial landmark dataset found in (Zhang et al., 2014).”
Learning Affinity via Spatial Propagation Networks (2017, methodology): “We use similarity transformation according to the results of 5-keypoint detection [35] to align all face images to the center.”
Deep Multi-task Representation Learning: A Tensor Factorisation Approach (2016, methodology): “This is in contrast to the conventional Deep-MTL approach of manually selecting a set of layers to undergo hard parameter sharing: by tying weights so each task uses exactly the same weight matrix/tensor for the corresponding layer (Zhang et al., 2014; Liu et al., 2015); and a set of layers to be co”
Adversarial Multi-task Learning for Text Classification (2017, background): “Recently, neuralbased models for multi-task learning have become very popular, ranging from computer vision (Misra et al., 2016; Zhang et al., 2014) to natural language processing (Collobert and Weston, 2008; Luong et al.”
Scalable Transfer Learning with Expert Models (2020, neutral): “Among others, this has been successfully applied to vision (Zhang et al., 2014), language (Liu et al.”
Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering (2017, methodology): “, unshared) decoders that extract labels for each task (Devin et al., 2016; Dong et al., 2015; Huang et al., 2013; 2015; Jaderberg et al., 2017; Liu et al., 2015a; Ranjan et al., 2016; Wu et al., 2015; Zhang et al., 2014) (Figure 1a).”
Multimodal News Article Analysis (2017, background): “Furthermore, recent work [Zhang et al., 2014] has shown that sharing a common representation to fulfill several tasks at the same time, can have unforeseen advantageous effects on each of the tasks, as the internal representation of the network can share the “capacities” learned for each one of the…”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, methodology): “For example, [12], [13], [37] use the input image as the CNN input and [57], [58] stack the image with a landmark response map as the input.”