부스트캠프 AI Tech/[Week6] Computer Vision (4) 썸네일형 리스트형 [Week6] Object Detection [Day5] *Object Detection 1.1 Fundamental image recognition tasks Semantic < Instance < Panoptic Semantic에서 동일한 클래스에서도 각각의 개체를 나눔 위 task를 수행하기 위해서는 object detection이 필요 1.2 What is object detection? classification bounding box 1.3 What are the applications of object detection? Autonomous driving Optical Character Recognition(OCR) 2. Two-stage detector 2.0 Traditional methods - hand - crafted techniques .. [Week6] Semantic segmentation [Day4] *What is semantic segmentation? Classify each pixel of an image into a category Don't care about instances. Only care about semantic category Applications Medical images Autonomous driving Computational photography *Semantic segmentation architectures Fully convolutional networks The first end-to-end architecture for semantic segmentation Take an image of an arbitrary size as input, and output a.. [Week6] CV - Image Classification Ⅱ [Day3] 1. Problems with deeper layers Alexnet -> VGGNet Deeper networks learn more powerful features, because of Larger receptive fields cf. receptive field : CNN에서 각 단계의 입력 이미지에 대해 하나의 필터가 커퍼할 수 있는 이미지 일부 More capacity and non-linearity But, getting deeper and deeper always works better? Deeper networks are harder to optimize Gradient vanishing / exploding Computationally complex Degradation problem (.. [Week6] CV - Image Classification Ⅰ[Day1] *What is computer vision? Machine Learning -> Deep Learning 패러다임 변화 Feature extraction을 자동적으로 수행하여 사람이 미처 보지 못한 특징들을 알아낼 수 있음 *Fundamental image tasks Deep Learning 기반의 task들 Data augmentation and Knowledge distillation Multi-modal learning (vision + {text, sound, 3D, etc.}) Conditional generative model Neural network analysis by visualization *What is classification classifier 세상의 모든 데이터를 가지고 있.. 이전 1 다음
