Log In Sign Up

Periocular in the Wild Embedding Learning with Cross-Modal Consistent Knowledge Distillation

by   Yoon Gyo Jung, et al.

Periocular biometric, or peripheral area of ocular, is a collaborative alternative to face, especially if a face is occluded or masked. In practice, sole periocular biometric captures least salient facial features, thereby suffering from intra-class compactness and inter-class dispersion issues particularly in the wild environment. To address these problems, we transfer useful information from face to support periocular modality by means of knowledge distillation (KD) for embedding learning. However, applying typical KD techniques to heterogeneous modalities directly is suboptimal. We put forward in this paper a deep face-to-periocular distillation networks, coined as cross-modal consistent knowledge distillation (CM-CKD) henceforward. The three key ingredients of CM-CKD are (1) shared-weight networks, (2) consistent batch normalization, and (3) a bidirectional consistency distillation for face and periocular through an effectual CKD loss. To be more specific, we leverage face modality for periocular embedding learning, but only periocular images are targeted for identification or verification tasks. Extensive experiments on six constrained and unconstrained periocular datasets disclose that the CM-CKD-learned periocular embeddings extend identification and verification performance by 50 face and periocular baselines. The experiments also reveal that the CM-CKD-learned periocular features enjoy better subject-wise cluster separation, thereby refining the overall accuracy performance.


page 2

page 7

page 13

page 15


Cross-modal knowledge distillation for action recognition

In this work, we address the problem how a network for action recognitio...

XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning

We present XKD, a novel self-supervised framework to learn meaningful re...

Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet)

Learning from different modalities is a challenging task. In this paper,...

Cross-modal Contrastive Distillation for Instructional Activity Anticipation

In this study, we aim to predict the plausible future action steps given...

Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?

This work digs into a root question in human perception: can face geomet...

Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition

Although the facial makeup transfer network has achieved high-quality pe...

Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices

This work focuses on the analysis that whether 3D face models can be lea...