Slides

Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers

Deep Learning Efficient AI

Tobias Christian Nauen

Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers

Presentation at WACV 2025 on a large-scale benchmark of 45+ transformer models for image classification, evaluating accuracy, speed, and memory efficiency.

WACV 2025 · 2025

Details Present

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax

Deep Learning Efficient AI

Tobias Christian Nauen

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax

Oral presentation at ICPR 2024 introducing TaylorShift, a novel reformulation of the attention mechanism using Taylor-Softmax that enables full token-to-token …

ICPR 2024 (oral) · 2024

Details Present

No decks match your filters