About
home
금융기술연구소
home

Resource Efficient Deep Learning for Computer Vision(RCV) Track 1, Budgeted Model Training Challenge

구분
챌린지
날짜
2023/10/02
시기
2023
게재처
ICCV 2023 Workshops
참여인원
Youngjun Kwak
Seonghun Jeong
Yunseung Lee
순위
1st
7 more properties

Abstract

The budgeted model training challenge aims to train an efficient classification model under resource limitations. To tackle this task in ImageNet-100, we describe a simple yet effective resource-aware backbone search framework composed of profile and instantiation phases. In addition, we employ multi-resolution ensembles to boost inference accuracy on limited resources. The profile phase obeys time and memory constraints to determine the models’ optimal batch-size, max epochs, and automatic mixed precision (AMP). And the instantiation phase trains models with the determined parameters from the profile phase. For improving intra-domain generalizations, the multi-resolution ensembles are formed by two-resolution images with randomly applied flips. We present a comprehensive analysis with expensive experiments. Based on our approach, we win first place in International Conference on Computer Vision (ICCV) 2023 Workshop Challenge Track 1 on Resource Efficient Deep Learning for Computer Vision (RCV).

카카오뱅크 금융기술연구소

Financial Tech Lab
Copyright ⓒ KakaoBank Corp. All rights reserved.