Research map / Label-efficient and robust learning / Semi-supervised learning
Margin-Mix: Semi–Supervised Learning for Face Expression Recognition
Corneliu Florea, Mihai Badea, Laura Florea, Andrei Racoviteanu, Constantin Vertan
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 sharpening temperature 0.25 instead of 0.5 (ablation) | MarginMix · FER+ (2000 labels) | accuracy (%): 55.35 -> 60.83 | Improved |
| add sharpening (T=0.25) versus none (ablation) | MarginMix · FER+ (2000 labels) | accuracy (%): 57.29 -> 60.83 | Improved |
| use soft self-labels instead of hard nearest-centroid labels (ablation) | MarginMix · FER+ (2000 labels) | accuracy (%): 51.87 -> 60.83 | Improved |
| use lambda_M=1 instead of 0.5 (ablation) | MarginMix · FER+ (2000 labels) | accuracy (%): 60.44 -> 60.83 | No clear effect |
| use N_aug 1024 instead of 512 (ablation) | MarginMix · FER+ (2000 labels) | accuracy (%): 60.68 -> 60.83 | No clear effect |
| add parameter EMA (ablation) | MarginMix · FER+ (2000 labels) | accuracy (%): 59.85 -> 60.83 | No clear effect |
| replace MixMatch with MarginMix | MarginMix · FER+ (320 labels) | accuracy (%): 45.60 -> 50.76 | Improved |
| replace MixMatch with MarginMix | MarginMix · FER+ (4000 labels) | accuracy (%): 70.91 -> 75.18 | Improved |
| replace MixMatch with MarginMix | MarginMix · RAF-DB (4000 labels) | accuracy (%): 65.24 -> 70.68 | Improved |
| replace MixMatch with MarginMix | MarginMix · CIFAR-10 (250 labels) | error (%): 11.80 -> 10.76 | Improved |
| replace MixMatch with MarginMix | MarginMix · CIFAR-10 (1000 labels) | error (%): 7.75 -> 8.33 | Hurt |
| replace MixMatch with MarginMix | MarginMix · CIFAR-100 (10000 labels) | error (%): 28.88 -> 29.12 | Hurt |
Later papers that compared with this method
1 later accepted paper reports MarginMix as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin (CVPR 2022 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MixMatch — MixMatch: A Holistic Approach to Semi-Supervised Learning (NeurIPS 2019) · better on 11 of 13 shared results
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
- Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin (CVPR 2022 · similarity 0.92)
- An Enhanced Adaptive Confidence Margin for Semi-Supervised Facial Expression Recognition (TPAMI 2025 · similarity 0.91)
- Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning (TPAMI 2021 · similarity 0.86)
- A Compact Embedding for Facial Expression Similarity (CVPR 2019 · similarity 0.86)
- Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States (ECCV 2018 · similarity 0.85)
- Masked Linear Regression for Learning Local Receptive Fields for Facial Expression Synthesis (IJCV 2019 · 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.
