CVCROct 12, 2022

Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistles

arXiv:2210.06529v134 citationsh-index: 65
Originality Incremental advance
AI Analysis

This addresses the challenge of matching face images across different sensing modalities, such as thermal to visible, which is useful for security and surveillance applications, and is incremental as it builds on existing FR models.

The paper tackles the problem of Heterogeneous Face Recognition (HFR) by proposing a Prepended Domain Transformer (PDT) block added to pre-trained face recognition models, achieving state-of-the-art performance on multiple benchmarks with minimal paired training samples.

Heterogeneous Face Recognition (HFR) refers to matching face images captured in different domains, such as thermal to visible images (VIS), sketches to visible images, near-infrared to visible, and so on. This is particularly useful in matching visible spectrum images to images captured from other modalities. Though highly useful, HFR is challenging because of the domain gap between the source and target domain. Often, large-scale paired heterogeneous face image datasets are absent, preventing training models specifically for the heterogeneous task. In this work, we propose a surprisingly simple, yet, very effective method for matching face images across different sensing modalities. The core idea of the proposed approach is to add a novel neural network block called Prepended Domain Transformer (PDT) in front of a pre-trained face recognition (FR) model to address the domain gap. Retraining this new block with few paired samples in a contrastive learning setup was enough to achieve state-of-the-art performance in many HFR benchmarks. The PDT blocks can be retrained for several source-target combinations using the proposed general framework. The proposed approach is architecture agnostic, meaning they can be added to any pre-trained FR models. Further, the approach is modular and the new block can be trained with a minimal set of paired samples, making it much easier for practical deployment. The source code and protocols will be made available publicly.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes