FiLM Conditioning

اشتراط FiLM

أسلوب لحقن معلومات الاشتراط (مثل المُشاهدات البصرية) في شبكة عصبية عبر تطبيق تحويل خطي (قياس وانزياح) على كل قناة في طبقات الالتفاف أو طبقات أخرى.

A technique for injecting conditioning information (such as visual observations) into a neural network by applying a learned affine transformation (scale and shift) to each channel in convolution or other layers.

Also translated asالتعديل الخطي السمِّي

First appears in this corpus in: Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (2022)

Appears in these papers

Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023 in the sky ✦
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding2022 in the sky ✦
Open X-Embodiment: Robotic Learning Datasets and RT-X Models2024 in the sky ✦