📢 검색 기능 추가 예정

23.04.06 (Thu)

Segment Anything
Meta AI Computer Vision Research
데이터 때려박아서 뭐든지 segmentation 하는 model / 현재 LLM이 성공한 방식 (데이터 때려박아서 모든 NLP task 씹어먹기)을 이미지 분야에 적용 / 내 졸논 방향과 비슷하고 졸논하면서 스치듯 느껴진 부분이었는데 실제로 나와버림,, / 그래도 핵심적인 졸논과의 차이점은 쟤네는 label이 엄청나게 필요한데 졸논 방법은 label 필요 없이 단순 이미지만 사용
[논문 정리] Segment Anything
* 작성자: 박진우 (GitHub) * GitHub: https://github.com/facebookresearch/segment-anything * Demo: https://segment-anything.com/demo * Blog: https://ai.facebook.com/blog/segment-anything-foundation-model-image-segmentation/ Motivation 최근 대규모의 언어 모델들은 놀라운 Zero-shot / Few-shot Generalization 성능을 보이고 있다…

Towards Healthy AI: Large Language Models Need Therapists Too 👀 TL;DR The paper presents the SafeguardGPT framework...

Posted by Daily Arxiv on Thursday, April 6, 2023

Great! You’ve successfully signed up.

Welcome back! You've successfully signed in.

You've successfully subscribed to zoomg.

Success! Check your email for magic link to sign-in.

Success! Your billing info has been updated.

Your billing was not updated.