Research

CLIP: Connecting text and images

Source: OpenAI News 05 Jan 2021

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GPT-2 and GPT-3.

Why It Matters

Pendekatan ini membolehkan aplikasi pantas ke tugas visual baru tanpa latihan khusus.

Keep Reading on NadiAI

Selected Related Articles