Research map / Architectures and efficiency / Attention and transformers
TransFER: Learning Relation-Aware Facial Expression Representations With Transformers
Fanglei Xue, Qiangchang Wang, Guodong Guo
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 local CNNs (multiple LANet branches) to ViT baseline (ablation) | TransFER · RAF-DB / AffectNet | accuracy: 89.93 -> 90.03 (RAF-DB), 65.63 -> 65.74 (AffectNet) | No clear effect |
| add MAD to local CNNs (ablation) | TransFER · RAF-DB | accuracy: 90.03 -> 90.35 | Improved |
| add MAD to local CNNs (ablation) | TransFER · AffectNet | mean class accuracy: 65.74 -> 65.94 | Improved |
| add MSAD (MAD in Transformer self-attention heads) (ablation) | TransFER · RAF-DB | accuracy: 90.35 -> 90.91 | Improved |
| add MSAD (MAD in Transformer self-attention heads) (ablation) | TransFER · AffectNet | mean class accuracy: 65.94 -> 66.23 | Improved |
| use IR-50 stage 3 instead of stage 2 as stem output (ablation) | TransFER · RAF-DB | accuracy: 84.94 -> 90.91 | Improved |
| use stage 3 instead of stage 4 of IR-50 (ablation) | TransFER · RAF-DB | accuracy: 90.32 -> 90.91 | Improved |
| set number of local branches B to 2 rather than a small value (ablation) | TransFER · RAF-DB | accuracy: 89.60 -> 90.91 | Improved |
| raise MAD drop rate p1 from 0.4 to 0.6 (p2=0.3) (ablation) | TransFER · RAF-DB | accuracy: 89.28 -> 90.91 | Improved |
| raise MSAD drop rate p2 from 0.1 to 0.3 (p1=0.6), then to 0.5 (ablation) | TransFER · RAF-DB | accuracy: 89.80 -> 90.91 -> 89.24 | Mixed |
| replace Dropout with MAD (ablation) | TransFER · RAF-DB | accuracy: 90.35 -> 90.91 | Improved |
| replace Drop Block with MAD (ablation) | TransFER · RAF-DB | accuracy: 90.25 -> 90.91 | Improved |
Later papers that compared with this method
1 later accepted paper reports transfer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks (AAAI 2026 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method (ICLR 2026 · similarity 0.88)
- Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning (TPAMI 2021 · similarity 0.88)
- Open-Set Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- PrefAce: Face-Centric Pretraining with Self-Structure Aware Distillation (AAAI 2024 · 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.
