Training Domain Specific Models for Energy-Efficient Object Detection

November 06, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, _init_paths.py, cfgs, data, demo-and-eval-save.py, demo_res101_coco.py, fig1_v2.jpg, gt.JPG, lib, make_dataset.py, models, normal_training_domain.py, output, script_makevoc.py, script_setup_dataset.py, test_eval.py, trainval_net_ds.py, xml_makelabels_domain.py, youtube.JPG

Authors Kentaro Yoshioka, Edward Lee, Mark Horowitz arXiv ID 1811.02689 Category cs.CV: Computer Vision Cross-listed cs.LG Citations 0 Venue arXiv.org Repository https://github.com/kentaroy47/training-domain-specific-models ⭐ 5 Last Checked 4 months ago

Abstract

We propose an end-to-end framework for training domain specific models (DSMs) to obtain both high accuracy and computational efficiency for object detection tasks. DSMs are trained with distillation \cite{hinton2015distilling} and focus on achieving high accuracy at a limited domain (e.g. fixed view of an intersection). We argue that DSMs can capture essential features well even with a small model size, enabling higher accuracy and efficiency than traditional techniques. In addition, we improve the training efficiency by reducing the dataset size by culling easy to classify images from the training set. For the limited domain, we observed that compact DSMs significantly surpass the accuracy of COCO trained models of the same size. By training on a compact dataset, we show that with an accuracy drop of only 3.6\%, the training time can be reduced by 93\%. The codes are uploaded in https://github.com/kentaroy47/training-domain-specific-models.