Research map / Image generation / Super-resolution
Anchored Regression Networks Applied to Age Estimation and Super Resolution
Eirikur Agustsson, Radu Timofte, Luc Van Gool
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 |
|---|---|---|---|
| replace DEX classification layer with ARN regression layer (101 anchors) | DEX pipeline · ChaLearn LAP validation (DEX IMDB-WIKI pretraining) | MAE (years): 3.252 -> 3.153 | Improved |
| replace DEX output layer with ARN (10 anchors) | DEX pipeline · ChaLearn LAP validation (DEX IMDB-WIKI pretraining) | MAE (years): 3.505 -> 3.237 | Improved |
| replace DEX output layer with ARN (101 anchors) starting from ImageNet VGG-16 | DEX pipeline · ChaLearn LAP validation (VGG-16 ImageNet pretraining) | MAE (years): 5.965 -> 4.947 | Improved |
| replace DEX with ARN (101 anchors) | DEX pipeline · MORPH 2 | MAE (years): 3.25 -> 3.00 | Improved |
| replace DEX with ARN when using IMDB-WIKI pretrained model | DEX pipeline · MORPH 2 (IMDB-WIKI pretrained) | MAE (years): 2.68 -> 2.63 | Improved |
| use 10 anchors instead of 101 when starting from ImageNet VGG-16 (ablation) | ARN · ChaLearn LAP validation (VGG-16 ImageNet pretraining) | MAE (years): 4.947 -> 4.516 | Improved |
| reduce DEX output neurons below 10 (ablation) | DEX · ChaLearn LAP validation | MAE vs number of outputs | Hurt |
| vary number of regressors in ARN (ablation) | ARN · ChaLearn LAP validation | MAE vs number of regressors | No clear effect |
| replace A+ with ARN (1024 regressors) | A+ · Set14 x3 SR | PSNR (dB): 29.13 -> 29.31 | Improved |
| replace A+ with ARN (1024 regressors) | A+ · Set5 x3 SR | PSNR (dB): 32.59 -> 32.89 | Improved |
| learn anchors jointly by gradients instead of closed-form global solution over fixed anchors (ablation) | ARN · Set5 x3 SR | PSNR (dB): 32.69 -> 32.89 | Improved |
| stack layers (Deep ARN, 7 x 16 regressors) instead of single ARN layer with 1024 regressors (ablation) | ARN · Set14 x3 SR | PSNR (dB): 29.31 -> 29.37 | Improved |
Closest papers by meaning
- BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation (CVPR 2019 · similarity 0.86)
- Ordinal Regression With Multiple Output CNN for Age Estimation (CVPR 2016 · similarity 0.84)
- Deep Regression Forests for Age Estimation (CVPR 2018 · similarity 0.84)
- Hierarchical Attention-Based Age Estimation and Bias Analysis (TPAMI 2023 · similarity 0.83)
- Age Progression and Regression with Spatial Attention Modules (AAAI 2020 · similarity 0.82)
- Lifespan Age Transformation Synthesis (ECCV 2020 · similarity 0.82)
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.
