RECORD
From Modalities to Styles: Rethinking the Domain Gap in Heterogeneous Face Recognition
Computer Vision and Pattern Recognition · Submitted 22 Apr 2024
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We extensively evaluate the proposed approach on various challenging HFR benchmarks, showing that it outperforms state-of-the-art methods.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Heterogeneous Face Recognition (HFR) focuses on matching faces from different domains, for instance, thermal to visible images, making Face Recognition (FR) systems more versatile for challenging scenarios. However, the domain gap between these domains and the limited large-scale datasets in the target HFR modalities make it challenging to develop robust HFR models from scratch. In our work, we view different modalities as distinct styles and propose a method to modulate feature maps of the target modality to address the domain gap. We present a new Conditional Adaptive Instance Modulation (CAIM ) module that seamlessly fits into existing FR networks, turning them into HFR-ready systems. The CAIM block modulates intermediate feature maps, efficiently adapting to the style of the source modality and bridging the domain gap. Our method enables end-to-end training using a small set of paired samples. We extensively evaluate the proposed approach on various challenging HFR benchmarks, showing that it outperforms state-of-the-art methods. The source code and protocols for reproducing the findings will be made publicly available
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Heterogeneous Face Recognition (HFR) focuses on matching faces from different domains, for instance, thermal to visible images, making Face Recognition (FR) systems more versatile for challenging scenarios. | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s1 | However, the domain gap between these domains and the limited large-scale datasets in the target HFR modalities make it challenging to develop robust HFR models from scratch. | background 0.72 | 0.07 | 0.02 | asserted 0.99 |
| s2 | In our work, we view different modalities as distinct styles and propose a method to modulate feature maps of the target modality to address the domain gap. | contribution 0.75 | 0.90 | 0.14 | asserted 0.98 |
| s3 | We present a new Conditional Adaptive Instance Modulation (CAIM ) module that seamlessly fits into existing FR networks, turning them into HFR-ready systems. | contribution 0.61 | 0.92 | 0.10 | asserted 1.00 |
| s4 | The CAIM block modulates intermediate feature maps, efficiently adapting to the style of the source modality and bridging the domain gap. | method 0.99 | 0.75 | 0.09 | asserted 1.00 |
| s5 | Our method enables end-to-end training using a small set of paired samples. | method 0.67 | 0.89 | 0.07 | asserted 0.96 |
| s6 | We extensively evaluate the proposed approach on various challenging HFR benchmarks, showing that it outperforms state-of-the-art methods. | result 1.00 | 0.96 | 0.76 | asserted 1.00 |
| s7 | The source code and protocols for reproducing the findings will be made publicly available | future work 0.70 | 0.31 | 0.03 | asserted 0.93 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Heterogeneous Face Recognition (HFR) focuses on matching faces from different domains, for instance, thermal to visible images, making Face Recognition (FR) systems more versatile for challenging scenarios. However, the domain gap between these domains and the limited large-scale datasets in the target HFR modalities make it challenging to develop robust HFR models from scratch. In our work, we view different modalities as distinct styles and propose a method to modulate feature maps of the target modality to address the domain gap. We present a new Conditional Adaptive Instance Modulation (CAIM ) module that seamlessly fits into existing FR networks, turning them into HFR-ready systems. The CAIM block modulates intermediate feature maps, efficiently adapting to the style of the source modality and bridging the domain gap. Our method enables end-to-end training using a small set of paired samples. We extensively evaluate the proposed approach on various challenging HFR benchmarks, showing that it outperforms state-of-the-art methods. The source code and protocols for reproducing the findings will be made publicly available
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
Papers whose main result relates to this one's
States the same result 1 paper
-
We extensively evaluate our approach on multiple challenging benchmarks, demonstrating superior performance compared to state-of-the-art methods.
Bridging the Gap: Heterogeneous Face Recognition with Conditional Adaptive Instance Modulation · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.