Research map / Image generation / Editing and style transfer
Residual Encoder Decoder Network and Adaptive Prior for Face Parsing
Tianchu Guo, Youngsung Kim, Hui Zhang, Deheng Qian, ByungIn Yoo, Jingtao Xu, Dongqing Zou, Jae-Joon Han, Changkyu Choi
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 |
|---|---|---|---|
| add adaptive prior (ablation) | RED-Net · Helen | overall F-measure: 0.903 -> 0.905 | Improved |
| add adaptive prior (ablation) | VGG-Deconv · Helen | overall F-measure: 0.874 -> 0.886 | Improved |
| use residual encoder instead of VGG encoder (ablation) | VGG-Deconv · Helen | overall F-measure: 0.874 -> 0.887 | Improved |
| use proposed residual decoder instead of plain deconvolution (ablation) | Res-Deconv · Helen | overall F-measure: 0.887 -> 0.903 | Improved |
| use implicit prior as network input instead of adaptive prior (ablation) | RED-Net · Helen | overall F-measure: 0.903 -> 0.887 | Hurt |
| remove detail-learning modules (random init) (ablation) | RD-Net · Helen | overall F-measure: 0.903 -> 0.833 | Hurt |
| remove detail-learning modules but init from full model (ablation) | RD-Net · Helen | overall F-measure: 0.903 -> 0.902 | No clear effect |
| remove densification modules (random init) (ablation) | RD-Net · Helen | overall F-measure: 0.903 -> 0.819 | Hurt |
| pretrain encoder on face recognition then use for parsing (RED-Net vs VGG-Deconv on LFW) (ablation) | RED-Net · LFW | pixel accuracy (%): 97.06 -> 97.59 | Improved |
| RED-Net vs Liu's on Helen | RED-Net · Helen | overall F-measure: 0.854 -> 0.905 | Improved |
Closest papers by meaning
- RED-Net: A Recurrent Encoder–Decoder Network for Video-Based Face Alignment (IJCV 2018 · similarity 0.88)
- A Recurrent Encoder-Decoder Network for Sequential Face Alignment (ECCV 2016 · similarity 0.88)
- Exploiting Semantics for Face Image Deblurring (IJCV 2020 · similarity 0.87)
- Face Parsing With RoI Tanh-Warping (CVPR 2019 · similarity 0.87)
- Residual Attribute Attention Network for Face Image Super-Resolution (AAAI 2019 · similarity 0.87)
- SegFace: Face Segmentation of Long-Tail Classes (AAAI 2025 · similarity 0.85)
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.
