Research map / Architectures and efficiency / CNN design
DAA: A Delta Age AdaIN Operation for Age Estimation via Binary Code Transformer
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add DAA operation (ablation) | ResNet18 age estimator · Morph | MAE: 2.72 -> 2.25 | Helped |
| add DAA operation (ablation) | ResNet18 age estimator · MegaAge-Asian | CA(3): 63.12 -> 68.82 | Helped |
| use multi-channel DAA with shared mean and standard deviation instead of single-channel DAA (ablation) | ResNet18+DAA · Morph | MAE: 2.65 -> 2.47 | Helped |
| use multi-channel DAA with shared mean and standard deviation instead of single-channel DAA (ablation) | ResNet18+DAA · MegaAge-Asian | CA(3): 67.97 -> 68.29 | Helped |
| replace age templates with binary code mapping (ablation) | ResNet18+DAA · Morph | MAE: 2.47 -> 2.25 | Helped |
| replace age templates with binary code mapping (ablation) | ResNet18+DAA · MegaAge-Asian | CA(3): 68.29 -> 68.82 | Helped |
| reduce test-time S/T samples from 100 to 2 (ablation) | ResNet18+DAA · MegaAge-Asian | MAE: 2.93 -> 2.95 | No clear effect |
| reduce test-time S/T samples from 100 to 2 (ablation) | ResNet18+DAA · MegaAge-Asian | CA(3): 68.82 -> 68.62 | No clear effect |
| add DAA to ResNet18 with pretraining | ResNet18 age estimator · Morph | MAE: 2.06$^{*}$; 1.94$^{*}$ | Mixed |
| add DAA to ResNet18 | ResNet18 age estimator · FG-Net | MAE: 2.19$^{*}$; 2.16$^{*}$ | Mixed |
| add DAA to ResNet18 | ResNet18 age estimator · MegaAge-Asian | CA(3): 68.82; 65.58 | Helped |
| add DAA to ResNet18 | ResNet18 age estimator · IMDB-clean | MAE: 5.27$^{*}$ -> 5.17 | Helped |
Closest papers by meaning
- A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark (CVPR 2024 · similarity 0.87)
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition (AAAI 2019 · similarity 0.87)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.86)
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 · similarity 0.86)
- Deep Regression Forests for Age Estimation (CVPR 2018 · similarity 0.86)
- AQUAFace: Age-Invariant Quality Adaptive Face Recognition for Unconstrained Selfie vs ID Verification (AAAI 2025 · similarity 0.83)
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.