1st Place in ICCV 2023 Workshop Challenge Track 1 on Resource Efficient Deep Learning for Computer Vision: Budgeted Model Training Challenge
This work addresses resource-efficient deep learning for computer vision, but it is incremental as it builds on existing methods for model optimization under constraints.
The paper tackled the problem of training an efficient classification model under resource constraints in the ImageNet-100 dataset, achieving first place in the ICCV 2023 workshop challenge by using a resource-aware backbone search framework and multi-resolution ensembles.
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).