Research map / Label-efficient and robust learning / Recognition and long-tail
Complex-Valued Iris Recognition Network
Kien Nguyen, Clinton Fookes, Sridha Sridharan, Arun A. Ross
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use two dense blocks instead of one (ablation) | ComplexIrisNet · ND-CrossSensor-2013 (validation) | FRR at FAR 0.1%: 2.84% -> 1.31% | Improved |
| use dense-block backbone instead of ResNet (ablation) | complex-valued iris network · ND-CrossSensor-2013 (validation) | FRR at FAR 0.1%: 1.68% -> 1.31% | Improved |
| use dense-block backbone instead of FeatNet (ablation) | complex-valued iris network · ND-CrossSensor-2013 (validation) | FRR at FAR 0.1%: 1.72% -> 1.31% | Improved |
| use complex-valued operations instead of real-valued counterparts (ablation) | ComplexIrisNet · ND-CrossSensor-2013 (validation) | FRR at FAR 0.1% | Improved |
| make FeatNet complex-valued | FeatNet · ND-CrossSensor-2013 (intra-dataset test) | FRR at FAR 0.1%: 1.79% -> 1.45% | Improved |
| make ResNet-style backbone complex-valued vs DRFNet | deep iris networks · UBIRIS.v2 (cross-dataset, no fine-tuning) | FRR at FAR 0.1%: 13.20% -> 12.33% | Improved |
| fine-tune on target dataset | Complex (ResNet backbone) · UBIRIS.v2 | FRR at FAR 0.1%: 12.33% -> 12.03% | Improved |
| fine-tune on target dataset | Complex (ResNet backbone) · CASIA-Iris-Thousand | FRR at FAR 0.1%: 3.70% -> 3.67% | No clear effect |
Closest papers by meaning
- Insights on ‘Complex-Valued Iris Recognition Network’ (TPAMI 2024 · similarity 0.89)
- Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features (ICCV 2017 · similarity 0.83)
- FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss Function (ICCV 2023 · similarity 0.82)
- ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications (CVPR 2026 · similarity 0.81)
- Co-Domain Symmetry for Complex-Valued Deep Learning (CVPR 2022 · similarity 0.80)
- Multilinear Operator Networks (ICLR 2024 · similarity 0.76)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
