Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

By Xuanyi Dong, Yezhou Yang. 2019

77 citations recorded by the source corpus.

Facial landmark detection aims to localize the anatomically defined points of human faces. In this paper, we study facial landmark detection from partially labeled facial images. A typical approach is to (1) train a detector on the labeled images; (2) generate new training samples using this detector's prediction as pseudo labels of unlabeled images; (3) retrain the detector on the labeled samples and partial pseudo labeled samples. In this way, the detector can learn from both labeled and unlabeled data and become robust. In this paper, we propose an interaction mechanism between a teacher and two students to generate more reliable pseudo labels for unlabeled data, which are beneficial to semi-supervised facial landmark detection. Specifically, the two students are instantiated as dual detectors. The teacher learns to judge the quality of the pseudo labels generated by the students and filter out unqualified samples before the retraining stage. In this way, the student detectors get feedback from their teacher and are retrained by premium data generated by itself. Since the two students are trained by different samples, a combination of their predictions will be more robust as the final prediction compared to either prediction. Extensive experiments on 300-W and AFLW benchmarks show that the interactions between teacher and students contribute to better utilization of the unlabeled data and achieves state-of-the-art performance.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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 Signal Processing

Citations in the corpus

Knowledge Distillation: A Survey (2020, background): “9g;Mullapudi et al.,2019; Siam et al., 2019; Dou et al., 2020), video classiﬁcation (Bhardwaj et al., 2019; Zhang and Peng, 2018), pedestrian detection (Shen et al., 2016), facial landmark detection (Dong and Yang, 2019), person re-identiﬁcation (Wu et al., 2019a) and person search (Munjal et al., 2”
3FabRec: Fast Few-Shot Face Alignment by Reconstruction (2019, background): “In [15], a teacher-supervisesstudents (TS(3)) framework is proposed in which a teacher is trained to filter student-generated landmark pseudolabels into ”qualified” and ”unqualified” samples, such that the student detectors can retrain themselves with better-quality data.”