In the low-temperature regime, the token distribution in mean-field transformers concentrates onto the push-forward under a key-query-value projection with Wasserstein distance scaling as √(log(β+1)/β) exp(Ct) + exp(-ct).
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Fusing quality scores from multiple intermediate transformer blocks in ViTs via depth-weighted averaging improves face image quality assessment on benchmarks without retraining or architecture changes.
ATTN-FIQA computes face image quality scores from pre-softmax attention patterns in pre-trained ViT-based FR models using a single forward pass, showing correlation with recognition utility and spatial interpretability.
citing papers explorer
-
Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
In the low-temperature regime, the token distribution in mean-field transformers concentrates onto the push-forward under a key-query-value projection with Wasserstein distance scaling as √(log(β+1)/β) exp(Ct) + exp(-ct).
-
EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment
Fusing quality scores from multiple intermediate transformer blocks in ViTs via depth-weighted averaging improves face image quality assessment on benchmarks without retraining or architecture changes.
-
ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers
ATTN-FIQA computes face image quality scores from pre-softmax attention patterns in pre-trained ViT-based FR models using a single forward pass, showing correlation with recognition utility and spatial interpretability.