부스트캠프 AI Tech/[Week7] Computer Vision (4) 썸네일형 리스트형 [Week7] 3D Understanding [Day5] 1. Seeing the world in 3D perspective 1.1 Why is 3D important? AI agents operate in the real world, which is a 3D space 3D applications - AR/VR 3D applications - 3D printing 3D applications - Medical applications 1.2 The way we observe 3D An image is a projection of the 3D world onto a 2D space Triangulation - The way to obtain a 3D point from 2D images 두 같은 지점과 카메라의 위치관계를 알고 있으면 3D 형상화가 가능 1.3 .. [Week7] Multi-modal Learning [Day4] 1. Overview of multi-modal learning Multi-modal Learning : 다른 특성을 갖는 데이터 타입들을 같이 활용하는 학습법(ex - text, sound) Challenge (1) - Different representations between modalities Audio - 1D Signal Image - 2D Array Text - Embedding vector Challenge (2) - Unbalance between heterogeneous feature spaces Challenge (3) - May a model be biased on a specific modality 명백한 데이터에 편향되고, 까다로운 데이터는 안써버리는 현상 발생 다양한 Chall.. [Week7] Conditional generative model [Day3] 1. Conditional generative model Translating an image given "condition" We can explicitly generate an image corresponding to a given "condition"! sketch of a bag이 주어졌을 때 X인 이미지가 일어날 확률 1.1 Generative model vs. Conditional generative model Generative model은 랜덤 샘플을 생성 Conditional generative model은 조건이 주어졌을 때 랜덤 샘플을 생성 Example of conditional generative model - audio super resolution P (high resoluti.. [Week7] Instance/Panoptic Segmentation and Landmark Localization [Day2] 1.Instance segmentation 1.1 What is instance segmentation? instance들 즉, 개체들까지 구분한 segmentation 1.2 Instance segmenters 기존 Faster R-CNN에서 Mask branch가 추가된 형태 기존 7x7x2048에서 14x14로 upsampling함과 동시에 채널수를 낮추고, 최종적으로 클래스의 갯수(80개) 만큼의 binary mask를 생성함 class단에서 나눈 정보를 참조하여 각 채널에서의 mask를 분류 Summary of the R-CNN family YOLACT (You Only Look At CoefficienTs) Real-time으로 instance segmentation이 가능한 single-st.. 이전 1 다음
