전체 글75 [2023-2] 염제원 - TASK2VEC: Task Embedding for Meta-Learning https://arxiv.org/abs/1902.03545 Task2Vec: Task Embedding for Meta-Learning We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those label arxiv.org Abstract Visual Classification Task에서 Task를 Vector로 표현하.. 2024. 1. 7. [2023-2] 주서영 - Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural network. However, the recent past has arxiv.org Abstract neural network 기반의 com.. 2024. 1. 2. [2023-2] 김동한 - Forecasting at scale https://peerj.com/preprints/3190.pdf Forecasting at Scale Facebook의 prophet 논문 리뷰 1. Abstract ● 예측(forecasting)은 데이터 사이언스에서 중요한 업무중 하나 ● 중요성에도 불구하고, 다양한 분야의 시계열 분야가 존재하고, 시계열 분석 전문가가 희귀함 ● 목적 : 해석이 가능한 parameter(모수), domain지식이 있는 사람은 직관적으로 조절가능하게 하는 모형(시계열 분석에 대한 전문성이 떨어지더라도) 2. Introduction 문제점 ● 완전한 자동예측 기술은 flexibility가 떨어져서, tuning하기 어렵고, 적절한 가정을 포함하기 힘듦 ● 도메인 지식이 깊은 전문가가 시계열에 대한 이해가 떨어지는 경우.. 2024. 1. 2. [2023-2] 현시은 - 3D image reconstruction from 2D CT slices(3DTV-CON2014) 원본 논문 링크 : https://ieeexplore.ieee.org/document/6874742 3D image reconstruction from 2D CT slices In this paper, a 3D reconstruction algorithm using CT slices of human pelvis is presented. We propose the method for 3D image reconstruction that is based on a combination of the SURF (Speeded-Up Robust Features) descriptor and SSD (Sum of Squared Differen ieeexplore.ieee.org Abstract 이 논문에서는 정확한 인체.. 2024. 1. 2. 이전 1 ··· 12 13 14 15 16 17 18 19 다음
