Fraunhofer's ViT-HarDis boosts face recognition by conditioning attention disentanglement on sample difficulty
FraunhoferIGD · hf · 2026-11-06
Fraunhofer IGD and TU Darmstadt propose ViT-HarDis, which conditions attention-head decorrelation on sample difficulty: hard face-recognition samples get stronger decorrelation regularization, applied only in the final transformer layers. This improves robust recognition without architectural changes or extra inference cost, unlike prior methods that penalize head correlations uniformly across all samples.
More from Research
- 99% Accuracy Can Be Useless: Why Precision and Recall Beat Accuracy in Fraud Detection — Franc0Fernand0 · 2026-11-06
- Joakim Sundnes' Open Textbook 'Introduction to Scientific Programming with Python' Lands on ChapterPal — burkov · 2026-11-06
- moyix releases slides from Offensive Con Tokyo talk: Fuzzing vs. AI — moyix · 2026-11-06
- Benchmark Error Bars Too Wide: Data Underpowered to Prove Recent AI Speedup — tobyordoxford · 2026-11-06
- TabClustPFN tops 44 real tabular clustering benchmarks, moving clustering into pretraining — jiqizhixin · 2026-11-06
- Attention as spherical interpolation: values combine inside the unit sphere before norm projects back — mgostIH · 2026-11-06