Keyword

zero-shot

2 papers tagged “zero-shot”

AIIEEE/CVF International Conference on Computer Vision (ICCV) · Apr 2023 Open access

Segment Anything

Alexander Kirillov, Eric Mintun and Nikhila Ravi

This paper introduces the Segment Anything project: a promptable image segmentation task, the Segment Anything Model (SAM), and the SA-1B dataset. SAM combines an image encoder, a flexible prompt encoder (points, boxes, masks, text), and a fast mask decoder to produce valid segmentation masks from arbitrary prompts. Trained on over 1 billion masks across 11 million images, SAM shows strong zero-shot transfer to many segmentation tasks without additional training.

computer vision image segmentation foundation model sam

AIOpenAI Technical Report · Feb 2019 Open access

Language Models are Unsupervised Multitask Learners

Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei and Ilya Sutskever

This paper introduces GPT-2, a 1.5-billion-parameter Transformer language model trained on a large web-text corpus (WebText) with a simple next-token prediction objective. It demonstrates that a sufficiently large language model can perform many NLP tasks in a zero-shot setting, without task-specific training data or fine-tuning. The work argued that unsupervised language modeling at scale implicitly learns to perform downstream tasks from naturally occurring demonstrations.

llm language modeling unsupervised learning zero-shot