PulseAugur
EN
LIVE 16:58:59

Foveated Dynamic Transformer mimics human vision for efficiency and robustness

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a Foveated Dynamic Transformer (FDT) inspired by the human visual system's foveated sampling and eye movements. This architecture dynamically selects tokens to process, enhancing efficiency and robustness against noise and adversarial attacks without specific training for these challenges. At a 50% fixation budget, the FDT demonstrated higher accuracy than DeiT-S while significantly reducing computational operations, showcasing a promising trade-off between accuracy and efficiency. AI

IMPACT This model's efficiency and robustness could lead to more adaptable and resilient AI systems in computer vision tasks.

RANK_REASON The cluster contains an academic paper detailing a new model architecture.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Foveated Dynamic Transformer mimics human vision for efficiency and robustness

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Ibrahim Batuhan Akkaya, Kishaan Jeeveswaran, Bahram Zonooz, Elahe Arani ·

    Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers

    arXiv:2607.09480v1 Announce Type: cross Abstract: The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources. Drawing inspiration from this robustness and adaptability, we…

  2. arXiv cs.LG TIER_1 English(EN) · Elahe Arani ·

    Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers

    The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources. Drawing inspiration from this robustness and adaptability, we introduce the Foveated Dynamic Transformer (FDT),…

RELATED ENTITIES

RELATED TOPICS