YOLOv8과 CLIP 기반의 Multi-modal 파이프라인을 통한 의약품 식별 자동화
From Pills to Pixels: Building an Intelligent Home Pharmacy Manager with YOLOv8 and CLIP 💊✨
From Pills to Pixels: Building an Intelligent Home Pharmacy Manager with YOLOv8 and CLIP 💊✨
Fine-tuning CLIP on a Niche Domain: How I Got +26pp Accuracy on Architectural Styles and What You Can Apply to Your Own Domain
[Day 5] My Cat-LoRA Got Worse With 45x More Photos. So I Figured Out Why and Fixed It.
LY Corporation이 전통 ML 모델과 멀티모달 LLM의 하이브리드 구조를 도입해 대규모 이미지 콘텐츠 모더레이션에서 정확도와 처리 속도 간 균형을 달성했다
Ethics and Society Newsletter #4: Bias in Text-to-Image Models
A Dive into Vision-Language Models
Zero-shot image segmentation with CLIPSeg
Fine tuning CLIP with Remote Sensing (Satellite) images and captions